INDEX

Explanations

words related to negotiation or conflict resolution

oai_token-act-pair · gpt-3.5-turbo

uncommon or complex word forms, particularly those with repetitive or unique consonant patterns

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

 Annotations

-0.69

 Integrity

-0.62

 Shuttle

-0.61

 Scand

-0.61

Ĥª

-0.60

 Awareness

-0.58

 Prin

-0.57

Wan

-0.57

Fen

-0.56

Nem

-0.55

POSITIVE LOGITS

ishly

1.02

efully

0.92

antly

0.91

kered

0.89

geoning

0.87

ingly

0.82

istically

0.81

icked

0.80

elled

0.80

aded

0.79

Activations Density 0.157%

words related to negotiation or conflict resolution

uncommon or complex word forms, particularly those with repetitive or unique consonant patterns

No Comments

No Known Activations