INDEX

Explanations

phrases related to warfare and military terms

oai_token-act-pair · gpt-3.5-turbo

references to warfare 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 @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ablishment

-0.73

ogene

-0.73

apo

-0.73

real

-0.73

utch

-0.73

idem

-0.71

clair

-0.71

thia

-0.71

jamin

-0.70

aye

-0.70

POSITIVE LOGITS

WAR

0.97

NER

0.97

RI

0.96

NING

0.95

MET

0.93

ER

0.89

CENT

0.88

 FANTASY

0.87

RAG

0.87

FIELD

0.86

Activations Density 0.006%

phrases related to warfare and military terms

references to warfare and military operations

No Comments

No Known Activations