INDEX

Explanations

instances where doubt is being cast on a statement or belief

oai_token-act-pair · gpt-3.5-turbo

instances of the word "doubt" and related expressions

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

ramid

-0.80

zie

-0.75

emetery

-0.71

ibrary

-0.70

ocument

-0.68

aternity

-0.66

Sov

-0.66

ummer

-0.66

ĺħ

-0.65

aml

-0.64

POSITIVE LOGITS

lessly

1.31

worthiness

0.99

fully

0.90

fulness

0.89

ingly

0.80

imaru

0.78

 doubt

0.76

bly

0.73

lessness

0.70

ful

0.70

Activations Density 0.018%

instances where doubt is being cast on a statement or belief

instances of the word "doubt" and related expressions

No Comments

No Known Activations