INDEX

Explanations

the word 'standard' in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to a "standard" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

Stars

-0.70

usters

-0.68

sie

-0.68

cig

-0.66

 Psychiat

-0.66

lez

-0.65

acan

-0.65

aska

-0.63

 Geological

-0.63

 Starship

-0.61

POSITIVE LOGITS

 deviation

1.21

 deviations

1.13

 bearer

1.05

 standard

0.93

ised

0.89

é¾įå¥ĳå£«

0.85

standard

0.84

izes

0.80

arily

0.78

essential

0.76

Activations Density 0.013%

the word 'standard' in various contexts

references to a "standard" in various contexts

No Comments

No Known Activations