INDEX

Explanations

phrases related to revealing information or exposing secrets

oai_token-act-pair · gpt-3.5-turbo

words related to repetition and revelation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

Io

-0.66

 à¨

-0.64

 Suffolk

-0.63

 Messenger

-0.60

 Danish

-0.59

 Fifth

-0.58

Doe

-0.57

 manager

-0.57

 Constable

-0.57

ucky

-0.57

POSITIVE LOGITS

lling

1.56

llers

1.51

ller

1.44

lled

1.29

xual

1.24

vable

1.19

ven

1.17

ved

1.17

cks

1.15

mented

1.14

Activations Density 0.094%

phrases related to revealing information or exposing secrets

words related to repetition and revelation

No Comments

No Known Activations