INDEX

Explanations

phrases that emphasize comparison or similarity

oai_token-act-pair · gpt-3.5-turbo

phrases that express comparisons or equivalences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

éĸ

-0.75

ðĿ

-0.74

livious

-0.72

ORPG

-0.65

ãĥ´ãĤ¡

-0.64

ãĢģ

-0.63

âķĲ

-0.62

 mediation

-0.62

 Flavoring

-0.62

 Recommended

-0.61

POSITIVE LOGITS

ever

0.78

 yourselves

0.69

0.66

 nearest

0.66

dies

0.66

borough

0.65

 possible

0.65

 weakest

0.65

wered

0.64

yip

0.64

Activations Density 0.123%

phrases that emphasize comparison or similarity

phrases that express comparisons or equivalences

No Comments

No Known Activations