INDEX

Explanations

mentions of health-related epidemics and their effects

oai_token-act-pair · gpt-3.5-turbo

terms related to epidemics and related issues

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

*/(

-0.87

wagen

-0.79

earchers

-0.79

nda

-0.77

lasses

-0.73

racuse

-0.73

partial

-0.72

yard

-0.71

endars

-0.70

akov

-0.70

POSITIVE LOGITS

 epidemic

1.13

 outbreak

0.99

 plag

0.97

 endemic

0.92

 Outbreak

0.91

 scourge

0.88

 Ebola

0.81

icity

0.80

 epidem

0.79

 plague

0.79

Activations Density 0.022%

mentions of health-related epidemics and their effects

terms related to epidemics and related issues

No Comments

No Known Activations