INDEX

Explanations

mentions of news sources

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

alities

-0.65

 inhib

-0.60

peak

-0.59

ting

-0.59

ghai

-0.58

terness

-0.58

aph

-0.56

 representing

-0.56

 intermedi

-0.55

eval

-0.54

POSITIVE LOGITS

atre

1.02

ater

0.96

odore

0.89

 latest

0.85

resa

0.79

 following

0.73

 Latest

0.71

aters

0.71

Score

0.71

 author

0.64

Activations Density 0.165%

mentions of news sources

occurrences of the word "the."

No Comments

No Known Activations