INDEX

Explanations

words related to instructions or advice

oai_token-act-pair · gpt-3.5-turbo

instances of the letter 'A' used in various contexts

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

arsity

-0.70

 Orient

-0.65

olicy

-0.64

 Everton

-0.64

Finish

-0.62

aneously

-0.62

evidence

-0.60

Merit

-0.59

 proceedings

-0.59

apesh

-0.58

POSITIVE LOGITS

cknowled

1.74

cknow

1.51

verages

1.24

lot

1.03

chieve

1.00

chie

0.98

 typical

0.98

 downside

0.97

 drawback

0.95

lyss

0.94

Activations Density 0.141%

words related to instructions or advice

instances of the letter 'A' used in various contexts

No Comments

No Known Activations