INDEX

Explanations

mentions of the word "fossil" or "fossil fuels."

oai_token-act-pair · gpt-3.5-turbo

references to fossil fuels

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

arta

-0.85

annis

-0.83

yang

-0.76

thel

-0.76

amber

-0.74

ansky

-0.73

urat

-0.72

ournal

-0.71

arter

-0.70

 Norton

-0.70

POSITIVE LOGITS

 fuels

1.13

 fuel

1.03

 fossil

0.94

ized

0.88

 Foss

0.88

fuel

0.85

 footprints

0.84

itions

0.83

ization

0.80

ifer

0.78

Activations Density 0.011%

mentions of the word "fossil" or "fossil fuels."

references to fossil fuels

No Comments

No Known Activations