INDEX

Explanations

comparisons where one option is explicitly contrasted with another

oai_token-act-pair · gpt-3.5-turbo

phrases that present contrasting ideas or alternatives

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enegger

-0.64

 FANT

-0.64

 Dahl

-0.61

boys

-0.60

redo

-0.59

 Kard

-0.59

 chairs

-0.57

 Semin

-0.57

fly

-0.56

mberg

-0.55

POSITIVE LOGITS

itably

0.79

 necessarily

0.73

 thereto

0.73

icip

0.72

arily

0.68

ifice

0.68

agonist

0.66

thodox

0.66

ively

0.66

oldown

0.63

Activations Density 0.025%

comparisons where one option is explicitly contrasted with another

phrases that present contrasting ideas or alternatives

No Comments

No Known Activations