INDEX

Explanations

keywords related to specific actions or instructions

oai_token-act-pair · gpt-3.5-turbo

topics related to specific products and industries

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aeda

-0.68

antha

-0.59

cule

-0.58

bos

-0.56

unin

-0.56

 guiActiveUnfocused

-0.55

hene

-0.55

VICE

-0.54

istine

-0.54

sem

-0.54

POSITIVE LOGITS

cellaneous

0.79

 meanwhile

0.78

.--

0.73

mbuds

0.72

!:

0.71

":{"

0.65

 Edit

0.65

 Lastly

0.63

 Functions

0.62

?:

0.61

Activations Density 1.026%

keywords related to specific actions or instructions

topics related to specific products and industries

No Comments

No Known Activations