INDEX

Explanations

mentions of "Veterans" or related terms in the context of military service or programs

oai_token-act-pair · gpt-3.5-turbo

mentions of veterans and related themes

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

wise

-0.73

mons

-0.72

Sty

-0.72

hran

-0.68

Drag

-0.65

lihood

-0.65

orie

-0.64

eton

-0.64

verages

-0.63

iang

-0.63

POSITIVE LOGITS

 Veterans

1.03

 veterans

0.95

 Affairs

0.84

 Veteran

0.81

 vets

0.78

 homelessness

0.74

 Memorial

0.74

 Benefits

0.71

 PTSD

0.71

roleum

0.70

Activations Density 0.018%

mentions of "Veterans" or related terms in the context of military service or programs

mentions of veterans and related themes

No Comments

No Known Activations