INDEX

Explanations

mentions of various types of deaths and related issues

oai_token-act-pair · gpt-3.5-turbo

references to fatalities or loss of life

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

acle

-0.71

ellig

-0.69

arity

-0.67

ellar

-0.67

asonic

-0.67

âĸ¬

-0.65

 Collider

-0.64

yrinth

-0.63

odes

-0.62

amina

-0.62

POSITIVE LOGITS

 attributable

0.95

 deaths

0.93

 attributed

0.92

icides

0.85

 toll

0.84

 Deaths

0.83

 occurring

0.81

 prevention

0.79

 aver

0.78

 Prevention

0.77

Activations Density 0.079%

mentions of various types of deaths and related issues

references to fatalities or loss of life

No Comments

No Known Activations