INDEX

Explanations

violent and graphic descriptions involving bodily harm

oai_token-act-pair · gpt-3.5-turbo

graphic descriptions of violence and injuries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ivals

-0.92

anguage

-0.72

vae

-0.69

 Families

-0.69

 Franch

-0.68

agents

-0.67

levard

-0.67

Bus

-0.67

 Reign

-0.65

 Pillar

-0.65

POSITIVE LOGITS

 protr

0.97

 hers

0.93

 amput

0.91

stretched

0.90

 swollen

0.90

 abnorm

0.86

 invol

0.84

 clenched

0.82

 numb

0.80

 Shutterstock

0.79

Activations Density 0.268%

violent and graphic descriptions involving bodily harm

graphic descriptions of violence and injuries

No Comments

No Known Activations