INDEX

Explanations

keywords related to programming variables or reserved words

oai_token-act-pair · gpt-3.5-turbo

references to programming concepts related to variables

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

furt

-0.86

ï¸

-0.80

éĥ

-0.80

llah

-0.78

Ķ

-0.78

AX

-0.77

ï¸ı

-0.77

lyak

-0.76

AME

-0.76

HCR

-0.76

POSITIVE LOGITS

 variables

0.86

variable

0.84

 variable

0.80

ially

0.77

uating

0.76

uates

0.74

 flares

0.73

staking

0.72

 Variable

0.71

etheless

0.69

Activations Density 0.016%

keywords related to programming variables or reserved words

references to programming concepts related to variables

No Comments

No Known Activations