INDEX

Explanations

instances where reasoning or questioning about a situation is being expressed

oai_token-act-pair · gpt-3.5-turbo

phrases that express confusion or questioning regarding circumstances or actions

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

catentry

-0.72

abase

-0.65

 attest

-0.63

aire

-0.62

 ILCS

-0.60

iggins

-0.59

 endif

-0.58

 icing

-0.58

onde

-0.56

 fide

-0.56

POSITIVE LOGITS

 bother

0.88

so

0.84

 bothered

0.84

 suddenly

0.80

ammed

0.75

so

0.73

forth

0.70

agna

0.69

 bothering

0.69

 chosen

0.69

Activations Density 0.514%

instances where reasoning or questioning about a situation is being expressed

phrases that express confusion or questioning regarding circumstances or actions

No Comments

No Known Activations