INDEX

Explanations

mentions of burning or being burnt

oai_token-act-pair · gpt-3.5-turbo

words related to burning or destruction by fire

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ournal

-0.72

onsense

-0.69

plom

-0.68

xus

-0.66

alian

-0.66

odore

-0.65

egal

-0.65

stood

-0.64

DonaldTrump

-0.64

Ĳ

-0.64

POSITIVE LOGITS

ished

1.06

ishing

1.01

 burning

0.96

 hotter

0.95

 burn

0.94

ishes

0.94

 burns

0.87

houses

0.85

 burned

0.85

burning

0.83

Activations Density 0.030%

mentions of burning or being burnt

words related to burning or destruction by fire

No Comments

No Known Activations