INDEX

Explanations

words related to medical procedures conducted after death

oai_token-act-pair · gpt-3.5-turbo

terms related to autopsies and post-mortem examinations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

env

-0.73

adding

-0.71

lessness

-0.70

Justin

-0.70

Ã±a

-0.65

Prince

-0.65

absolute

-0.64

FUL

-0.64

acted

-0.64

Wil

-0.63

POSITIVE LOGITS

 autopsy

1.00

mortem

0.86

iology

0.81

 disse

0.79

 Canaver

0.78

 examinations

0.78

opsy

0.78

 examination

0.75

illac

0.74

ufact

0.71

Activations Density 0.010%

words related to medical procedures conducted after death

terms related to autopsies and post-mortem examinations

No Comments

No Known Activations