INDEX

Explanations

occurrences of the word "Dot" in the text

oai_token-act-pair · gpt-3.5-turbo

mentions of specific media content, particularly games and devices

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

Not in Any Lists

No Comments

Negative Logits

eele

-0.76

ivals

-0.72

uberty

-0.71

éĹĺ

-0.69

iscopal

-0.68

IENCE

-0.67

 obser

-0.67

ocene

-0.67

reditary

-0.67

issance

-0.66

POSITIVE LOGITS

Dot

1.06

zeb

0.95

amphetamine

0.84

zh

0.83

lings

0.80

dot

0.78

wana

0.73

yond

0.72

izens

0.71

TY

0.69

Activations Density 0.014%

occurrences of the word "Dot" in the text

mentions of specific media content, particularly games and devices

No Comments

No Known Activations