INDEX

Explanations

phrases related to common occurrences or established situations

oai_token-act-pair · gpt-3.5-turbo

references to common or typical scenarios

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

mented

-0.79

acus

-0.79

rea

-0.75

ï¸ı

-0.74

atoon

-0.73

wic

-0.71

vic

-0.66

Ship

-0.66

zon

-0.66

isine

-0.64

POSITIVE LOGITS

 suspects

0.97

 caveats

0.93

 disclaimer

0.92

 caveat

0.87

 assumption

0.85

 disclaim

0.80

 refrain

0.80

 wisdom

0.80

 explanation

0.80

 tropes

0.79

Activations Density 0.090%

phrases related to common occurrences or established situations

references to common or typical scenarios

No Comments

No Known Activations