INDEX

Explanations

words related to processes involving heat or cooking

oai_token-act-pair · gpt-3.5-turbo

terms related to boiling and cooking processes

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

ngth

-0.88

ournal

-0.88

stood

-0.78

dfx

-0.78

prises

-0.78

mble

-0.75

eele

-0.74

 ende

-0.74

alez

-0.74

 Agency

-0.74

POSITIVE LOGITS

 boiling

1.14

 boils

1.12

 boiled

1.10

 boil

1.07

 kettle

0.99

 simmer

0.95

stall

0.79

 stove

0.79

SourceFile

0.76

 arsenic

0.75

Activations Density 0.022%

words related to processes involving heat or cooking

terms related to boiling and cooking processes

No Comments

No Known Activations