INDEX

Explanations

words related to military actions and historical conflicts

oai_token-act-pair · gpt-3.5-turbo

mentions of sieges or situations of being under siege

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

aunder

-0.95

uana

-0.87

ioch

-0.81

ortium

-0.80

 Tradable

-0.78

arrell

-0.78

ortality

-0.78

ittees

-0.77

ocr

-0.75

arette

-0.75

POSITIVE LOGITS

 siege

1.00

 Siege

0.92

 bombard

0.88

 bombardment

0.88

eers

0.83

 barrage

0.82

 besie

0.79

 barr

0.78

hammer

0.75

 besieged

0.74

Activations Density 0.026%

words related to military actions and historical conflicts

mentions of sieges or situations of being under siege

No Comments

No Known Activations