INDEX

Explanations

keywords related to military combat or warfare

oai_token-act-pair · gpt-3.5-turbo

terms related to combat and military operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gow

-0.75

eus

-0.72

 explan

-0.69

Zot

-0.66

 coerc

-0.66

Boh

-0.65

 Juda

-0.64

 Rosenstein

-0.64

esta

-0.62

ħĭ

-0.62

POSITIVE LOGITS

ant

1.33

ants

1.22

iveness

1.00

ting

0.95

 readiness

0.93

ments

0.89

 fatig

0.86

 zones

0.83

forces

0.83

fighter

0.82

Activations Density 0.073%

keywords related to military combat or warfare

terms related to combat and military operations

No Comments

No Known Activations