INDEX

Explanations

mentions of military troops in different contexts

oai_token-act-pair · gpt-3.5-turbo

references to military troops and their deployment

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

âĸ¬

-0.75

theless

-0.73

MAL

-0.71

sight

-0.70

ities

-0.70

 Literary

-0.67

 Mercury

-0.65

lihood

-0.65

Consumer

-0.65

£ı

-0.63

POSITIVE LOGITS

 stationed

1.27

 garrison

1.01

 fatig

0.97

 deployed

0.95

 patrolling

0.90

 troops

0.89

opers

0.88

 barracks

0.87

 troop

0.86

 deployments

0.86

Activations Density 0.027%

mentions of military troops in different contexts

references to military troops and their deployment

No Comments

No Known Activations