INDEX

Explanations

terms related to causes of death in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to the concept of death

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Plex

-0.75

Alpha

-0.72

İ

-0.66

ellig

-0.65

arity

-0.63

PLA

-0.63

Stud

-0.62

Cola

-0.62

afort

-0.61

agall

-0.61

POSITIVE LOGITS

 deaths

0.84

 toll

0.83

 overdoses

0.78

hooting

0.78

umatic

0.75

icides

0.75

bage

0.72

afe

0.72

hips

0.72

 Deaths

0.70

Activations Density 0.040%

terms related to causes of death in various contexts

references to the concept of death

No Comments

No Known Activations