INDEX

Explanations

words related to violence and conflict

oai_token-act-pair · gpt-3.5-turbo

references to different forms of "raw" material or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ŃĶ

-0.85

 Normandy

-0.65

uated

-0.65

uate

-0.65

ossession

-0.64

 bubble

-0.64

 Amend

-0.64

ucky

-0.64

arios

-0.64

eanor

-0.62

POSITIVE LOGITS

raw

1.28

Pic

0.88

TPPStreamerBot

0.88

esome

0.86

lings

0.83

sth

0.83

inning

0.82

MpServer

0.81

RAW

0.80

ls

0.80

Activations Density 0.003%

words related to violence and conflict

references to different forms of "raw" material or experiences

No Comments

No Known Activations