INDEX

Explanations

mentions of military-related terms and activities

oai_token-act-pair · gpt-3.5-turbo

words related to military contexts or military actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Bake

-0.87

çīĪ

-0.67

 orally

-0.66

 miscarriage

-0.65

Dip

-0.64

 pasture

-0.63

 tasting

-0.62

ITED

-0.62

Lot

-0.62

swer

-0.61

POSITIVE LOGITS

arily

1.38

ament

1.35

aries

1.22

iam

1.20

ancy

1.18

aments

1.15

arist

1.14

aires

1.12

antly

1.08

agement

1.06

Activations Density 0.038%

mentions of military-related terms and activities

words related to military contexts or military actions

No Comments

No Known Activations