INDEX

Explanations

phrases indicating intention or preference

oai_token-act-pair · gpt-3.5-turbo

expressions of desire or intent

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

 elabor

-0.69

aughs

-0.68

laughter

-0.66

 mentions

-0.63

 suggests

-0.61

 suggestion

-0.61

inis

-0.59

 argues

-0.59

 cited

-0.58

esters

-0.58

POSITIVE LOGITS

"))

0.81

 âī¡

0.66

omething

0.65

achable

0.65

safe

0.64

qualified

0.63

 trustworthy

0.63

ãģª

0.62

aterial

0.62

 sooner

0.62

Activations Density 0.783%

phrases indicating intention or preference

expressions of desire or intent

No Comments

No Known Activations