INDEX

Explanations

the word "to" preceding a verb

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate opportunities or permissions

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

 heartbeat

-0.69

 Beng

-0.64

 Rahman

-0.60

CI

-0.59

 foss

-0.58

audi

-0.58

 evid

-0.57

 casing

-0.57

Statement

-0.57

ials

-0.56

POSITIVE LOGITS

asted

0.98

wered

0.86

 grips

0.86

otom

0.79

asty

0.78

 settle

0.77

axy

0.75

fman

0.71

iled

0.70

istered

0.70

Activations Density 0.074%

the word "to" preceding a verb

phrases that indicate opportunities or permissions

No Comments

No Known Activations