INDEX

Explanations

terms related to military actions or entities

oai_token-act-pair · gpt-3.5-turbo

mentions of military-related topics or terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

âĶģ

-0.87

nob

-0.80

gger

-0.80

DAY

-0.75

Filename

-0.74

apest

-0.73

galitarian

-0.73

orative

-0.72

heimer

-0.72

POSITIVE LOGITS

 fatig

1.09

 commanders

1.00

 personnel

0.96

 dictatorship

0.95

 acad

0.91

 stationed

0.89

 barracks

0.89

 commander

0.88

 contractor

0.88

 coup

0.87

Activations Density 0.046%

terms related to military actions or entities

mentions of military-related topics or terms

No Comments

No Known Activations