INDEX

Explanations

words related to cause and effect or logical reasoning

oai_token-act-pair · gpt-3.5-turbo

punctuation that indicates transitions or conclusions in arguments

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

OTHER

-0.63

Pont

-0.62

ãĥ¥

-0.62

Redd

-0.62

gaard

-0.61

ULAR

-0.61

blank

-0.60

Really

-0.60

NBA

-0.60

roy

-0.59

POSITIVE LOGITS

 according

0.97

 although

0.94

 however

0.85

 whereas

0.81

 unless

0.81

 despite

0.80

 unlike

0.79

 contrary

0.78

 whenever

0.74

if

0.74

Activations Density 0.185%

words related to cause and effect or logical reasoning

punctuation that indicates transitions or conclusions in arguments

No Comments

No Known Activations