INDEX

Explanations

adjectives that describe the complexity or clarity of a concept

oai_token-act-pair · gpt-3.5-turbo

terms that indicate simplicity or clarity in complex contexts

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

deen

-0.62

thood

-0.60

ioxide

-0.60

 position

-0.60

agine

-0.60

tein

-0.59

assies

-0.56

 Statue

-0.56

ench

-0.54

Ķ

-0.53

POSITIVE LOGITS

 enough

1.21

 insofar

0.98

 nonetheless

0.98

enough

0.87

 because

0.81

but

0.81

 indeed

0.80

 nevertheless

0.79

 despite

0.76

Activations Density 0.388%

adjectives that describe the complexity or clarity of a concept

terms that indicate simplicity or clarity in complex contexts

No Comments

No Known Activations