INDEX

Explanations

instances of the word "ign" with varying degrees of intensity

oai_token-act-pair · gpt-3.5-turbo

instances and variations of the word "sign" in different contexts

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

bian

-0.78

HAHAHAHA

-0.75

cham

-0.74

 Mighty

-0.73

 Springfield

-0.70

 Span

-0.65

Wem

-0.65

Bie

-0.63

HAHA

-0.62

 Gingrich

-0.62

POSITIVE LOGITS

ments

1.10

ificant

1.05

antly

1.03

eous

1.00

ame

0.97

ified

0.96

entials

0.94

atories

0.92

mentation

0.89

atures

0.88

Activations Density 0.019%

instances of the word "ign" with varying degrees of intensity

instances and variations of the word "sign" in different contexts

No Comments

No Known Activations