INDEX

Explanations

proper nouns related to people

oai_token-act-pair · gpt-3.5-turbo

prominent names and figures in various contexts

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

sen

-1.10

aic

-0.97

enic

-0.94

ions

-0.91

fully

-0.89

ory

-0.89

tumblr

-0.86

iar

-0.86

rine

-0.85

imar

-0.84

POSITIVE LOGITS

é¾įå¥ĳå£«

0.80

 Beir

0.73

 drawer

0.71

 siph

0.65

selage

0.64

 hunter

0.63

 Bout

0.62

 Ples

0.62

 Alonso

0.62

 Solitaire

0.62

Activations Density 0.216%

proper nouns related to people

prominent names and figures in various contexts

No Comments

No Known Activations