INDEX

Explanations

mentions of euthanizing or related terms

oai_token-act-pair · gpt-3.5-turbo

references to euthanasia

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

 Dynamics

-0.73

 Belt

-0.72

Ø§ÙĦ

-0.71

 Soda

-0.70

 Painter

-0.69

 Dress

-0.66

 Pell

-0.65

Brand

-0.65

 Collider

-0.65

 Shirt

-0.64

POSITIVE LOGITS

anasia

1.56

 euth

0.95

onym

0.91

umatic

0.84

rieved

0.83

oenix

0.83

umbn

0.82

isec

0.80

onomic

0.79

ADRA

0.77

Activations Density 0.021%

mentions of euthanizing or related terms

references to euthanasia

No Comments

No Known Activations