INDEX

Explanations

the word "no" followed by other words or phrases

oai_token-act-pair · gpt-3.5-turbo

negations or phrases indicating absence or lack of something

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

RAFT

-0.78

assies

-0.75

rex

-0.66

lycer

-0.66

gnu

-0.66

adobe

-0.65

iership

-0.65

dor

-0.64

aven

-0.63

ommod

-0.62

POSITIVE LOGITS

xious

1.25

 longer

1.07

 doubt

1.00

 matter

0.96

except

0.95

oses

0.90

 indication

0.87

 conceivable

0.83

oooooooo

0.83

 guarantee

0.83

Activations Density 0.093%

the word "no" followed by other words or phrases

negations or phrases indicating absence or lack of something

No Known Activations