INDEX

Explanations

violent or conflicting situations

oai_token-act-pair · gpt-3.5-turbo

words and phrases related to torment and related actions

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

enegger

-0.72

PRES

-0.67

 Idle

-0.64

 Consent

-0.64

 McGill

-0.64

OPA

-0.64

éļ

-0.63

stakes

-0.62

DragonMagazine

-0.62

ynski

-0.62

POSITIVE LOGITS

mented

0.93

onto

0.87

onite

0.82

rid

0.81

vell

0.81

ritch

0.81

rums

0.78

orable

0.77

anz

0.77

ched

0.76

Activations Density 0.015%

violent or conflicting situations

words and phrases related to torment and related actions

No Comments

No Known Activations