INDEX

Explanations

the word "to" with high activation values

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "seems to."

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

 Rapids

-0.68

estern

-0.68

opens

-0.66

loads

-0.65

bats

-0.65

blooded

-0.63

ashes

-0.63

earable

-0.61

 Plain

-0.61

ãĤ¦ãĤ¹

-0.61

POSITIVE LOGITS

 embody

0.97

 indicate

0.96

 imply

0.90

 settle

0.89

be

0.89

 differentiate

0.88

 derive

0.87

 have

0.86

 defy

0.86

 belong

0.86

Activations Density 0.075%

the word "to" with high activation values

instances of the phrase "seems to."

No Comments

No Known Activations