INDEX

Explanations

names of individuals, particularly surnames

oai_token-act-pair · gpt-3.5-turbo

names of people and places related to specific individuals

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

itcher

-0.70

akia

-0.67

 Twain

-0.67

hh

-0.65

irts

-0.63

":["

-0.63

 repayment

-0.62

iage

-0.62

ika

-0.61

ither

-0.61

POSITIVE LOGITS

atech

0.86

urses

0.78

olls

0.77

ursed

0.74

aught

0.74

agher

0.73

acci

0.71

onut

0.71

ption

0.70

rete

0.70

Activations Density 0.036%

names of individuals, particularly surnames

names of people and places related to specific individuals

No Comments

No Known Activations