INDEX

Explanations

personal pronouns and words related to doubt

oai_token-act-pair · gpt-3.5-turbo

references to quantities or groups of items

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

ÃĥÃĤ

-0.68

Ö¼

-0.66

oru

-0.66

Newsletter

-0.65

ģ«

-0.63

iker

-0.63

ezvous

-0.63

ister

-0.63

atown

-0.63

opsis

-0.63

POSITIVE LOGITS

nuts

0.87

 facets

0.82

odd

0.76

nut

0.75

ties

0.72

usions

0.70

aire

0.70

together

0.69

uding

0.69

eties

0.69

Activations Density 0.046%

personal pronouns and words related to doubt

references to quantities or groups of items

No Comments

No Known Activations