INDEX

Explanations

phrases related to progress and change

oai_token-act-pair · gpt-3.5-turbo

references to notable figures or events in discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Ago

-0.68

 Fold

-0.65

atown

-0.61

 Moves

-0.61

ccording

-0.56

ournal

-0.56

 Mons

-0.55

aukee

-0.55

 Work

-0.55

 Cous

-0.54

POSITIVE LOGITS

 accordingly

1.60

 consequently

1.15

 therein

1.05

 thereafter

1.05

 thereof

1.02

 thereto

0.98

 therefore

0.92

 consequ

0.89

 alike

0.85

 damned

0.79

Activations Density 0.625%

phrases related to progress and change

references to notable figures or events in discussions

No Comments

No Known Activations