INDEX

Explanations

parentheses followed by numbers

oai_token-act-pair · gpt-3.5-turbo

punctuation marks, particularly closing parentheses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

aban

-0.71

rogens

-0.65

hor

-0.64

udos

-0.64

endo

-0.64

kus

-0.63

iku

-0.63

roxy

-0.61

rogen

-0.61

POSITIVE LOGITS

 comprising

0.64

anship

0.63

 which

0.62

 namely

0.62

channelAvailability

0.61

 implying

0.60

————

0.60

 however

0.59

ordable

0.59

 whichever

0.59

Activations Density 0.080%

parentheses followed by numbers

punctuation marks, particularly closing parentheses

No Comments

No Known Activations