INDEX

Explanations

mentions of acts of violence or deaths of individuals

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "killed" related to violent events or deaths

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

rium

-0.81

DragonMagazine

-0.79

idth

-0.76

ĨĴ

-0.71

Cola

-0.67

users

-0.63

SPONSORED

-0.60

Applic

-0.60

Factor

-0.60

Club

-0.60

POSITIVE LOGITS

by

0.92

 spree

0.89

 fighting

0.83

 unarmed

0.80

 tragically

0.79

 rampage

0.78

 wounding

0.74

fighting

0.74

 instantly

0.74

 innoc

0.74

Activations Density 0.067%

mentions of acts of violence or deaths of individuals

occurrences of the word "killed" related to violent events or deaths

No Comments

No Known Activations