INDEX

Explanations

instances where an action or modification can be made

oai_token-act-pair · gpt-3.5-turbo

phrases indicating capability or possibility

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pires

-0.68

 Hits

-0.68

burgh

-0.66

 Mant

-0.65

 Strikes

-0.65

 Appears

-0.63

arthed

-0.62

 favors

-0.62

 forthcoming

-0.62

 Attention

-0.62

POSITIVE LOGITS

't

1.55

NOT

1.16

 choose

1.00

 customize

0.99

 find

0.96

 optionally

0.95

 expect

0.94

 learn

0.91

berra

0.91

ister

0.91

Activations Density 0.104%

instances where an action or modification can be made

phrases indicating capability or possibility

No Comments

No Known Activations