INDEX

Explanations

sentences or phrases with specific patterns of characters

oai_token-act-pair · gpt-3.5-turbo

references to time and control events

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

ichick

-0.68

hens

-0.63

etsk

-0.62

lists

-0.60

vention

-0.59

asty

-0.59

onomous

-0.59

ach

-0.59

ittal

-0.58

ery

-0.58

POSITIVE LOGITS

 EDITION

1.27

HAM

1.19

URA

1.17

AGES

1.14

HEAD

1.12

MENT

1.12

WOR

1.11

LET

1.11

EY

1.10

WAR

1.09

Activations Density 0.251%

sentences or phrases with specific patterns of characters

references to time and control events

No Comments

No Known Activations