INDEX

Explanations

phrases related to fires and incidents involving fire

oai_token-act-pair · gpt-3.5-turbo

references to fire incidents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

xus

-0.99

 Vide

-0.73

 Virtue

-0.73

 Lans

-0.73

pes

-0.71

kees

-0.66

 Freed

-0.65

atever

-0.64

atem

-0.64

 propri

-0.63

POSITIVE LOGITS

 exting

1.27

fighting

1.21

storm

1.19

storms

1.12

balls

1.07

proof

1.04

bomb

1.02

fight

1.02

flies

1.00

wood

1.00

Activations Density 0.035%

phrases related to fires and incidents involving fire

references to fire incidents

No Comments

No Known Activations