INDEX

Explanations

mention of violent actions, particularly stabbings

oai_token-act-pair · gpt-3.5-turbo

terms related to stabbing incidents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

mberg

-0.78

 Administ

-0.69

 Organization

-0.69

XM

-0.68

 Cosmos

-0.68

 Leban

-0.66

oS

-0.65

administ

-0.65

tz

-0.64

BuyableInstoreAndOnline

-0.63

POSITIVE LOGITS

lished

1.09

 wounds

1.00

 slit

0.89

 stab

0.86

 spree

0.84

 rampage

0.82

nesday

0.79

 stabbing

0.79

 dagger

0.78

 wound

0.77

Activations Density 0.030%

mention of violent actions, particularly stabbings

terms related to stabbing incidents

No Comments

No Known Activations