INDEX

Explanations

a specific pattern in the text, specifically the abbreviation "UP" followed by a number, potentially related to locations or organizations

oai_token-act-pair · gpt-3.5-turbo

the abbreviation "UP" indicating the University Press or related institutions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 resonance

-0.65

 enclosed

-0.65

croft

-0.62

wagen

-0.60

rosso

-0.60

paio

-0.59

azer

-0.58

avia

-0.58

 Camel

-0.58

 Murdoch

-0.58

POSITIVE LOGITS

PER

1.22

olicy

1.09

PDATE

1.07

ERT

1.04

ERN

0.95

IED

0.94

FER

0.93

PLIC

0.93

rompt

0.91

LOAD

0.91

Activations Density 0.011%

a specific pattern in the text, specifically the abbreviation "UP" followed by a number, potentially related to locations or organizations

the abbreviation "UP" indicating the University Press or related institutions

No Comments

No Known Activations