INDEX

Explanations

mentions of how something is done or how something works in various contexts

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cise

-0.79

ername

-0.78

ategory

-0.78

nit

-0.78

dn

-0.75

tesy

-0.74

plete

-0.73

ca

-0.72

Ļ½

-0.72

mediate

-0.71

POSITIVE LOGITS

 heck

1.09

 hell

0.95

 disparate

0.87

 pend

0.87

 tide

0.87

 curtain

0.85

 world

0.82

 fuck

0.81

 tides

0.80

 universe

0.80

Activations Density 0.214%

mentions of how something is done or how something works in various contexts

occurrences of the word "the."

No Comments

No Known Activations