INDEX

Explanations

phrases related to emphasis or progression

oai_token-act-pair · gpt-3.5-turbo

punctuation that indicates significant pauses or breaks in thoughts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Wire

-0.76

SourceFile

-0.75

coat

-0.74

bern

-0.73

enta

-0.72

usterity

-0.70

OHN

-0.68

eni

-0.68

ighed

-0.67

ĻĤ

-0.67

POSITIVE LOGITS

 acquies

0.65

 concede

0.63

 congratulate

0.63

 guessed

0.62

 speculate

0.62

 withdrew

0.62

 expects

0.61

 somew

0.61

 enshr

0.60

tre

0.59

Activations Density 0.134%

phrases related to emphasis or progression

punctuation that indicates significant pauses or breaks in thoughts

No Comments

No Known Activations