INDEX

Explanations

mentions of diseases

oai_token-act-pair · gpt-3.5-turbo

terms and references related to disease

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ruce

-0.85

ilts

-0.77

anian

-0.76

endas

-0.74

adra

-0.74

idav

-0.74

assy

-0.72

adesh

-0.72

ramid

-0.70

aird

-0.68

POSITIVE LOGITS

 disease

1.00

 Immun

0.99

 outbreak

0.96

 diseases

0.96

 prevention

0.91

 Outbreak

0.91

 outbreaks

0.89

 Diseases

0.85

 Disease

0.85

 infections

0.82

Activations Density 0.014%

mentions of diseases

terms and references related to disease

No Comments

No Known Activations