INDEX

Explanations

hints or suggestions

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate a suggestion or indication of something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ocker

-0.79

nea

-0.78

ccording

-0.74

 martyr

-0.69

ctic

-0.67

animate

-0.66

frey

-0.65

vict

-0.65

 reckoned

-0.64

die

-0.63

POSITIVE LOGITS

 hint

1.51

 hints

1.40

 clue

0.90

 clues

0.85

 hinted

0.83

itives

0.77

 wink

0.74

ibility

0.72

endum

0.72

 warning

0.71

Activations Density 0.013%

hints or suggestions

phrases that indicate a suggestion or indication of something

No Comments

No Known Activations