INDEX

Explanations

references to violent incidents, specifically shootings

oai_token-act-pair · gpt-3.5-turbo

references to incidents of gun violence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hw

-0.82

Label

-0.79

undai

-0.74

ebook

-0.73

Yok

-0.72

ateg

-0.71

akuya

-0.70

MpServer

-0.70

GY

-0.70

ulla

-0.69

POSITIVE LOGITS

 shooting

1.03

 spree

1.01

 shoot

0.93

 Shooting

0.84

powder

0.82

nikov

0.80

 shoots

0.80

 Shoot

0.79

 gallery

0.78

 fireworks

0.77

Activations Density 0.016%

references to violent incidents, specifically shootings

references to incidents of gun violence

No Comments

No Known Activations