INDEX

Explanations

adjectives and nouns related to personal attributes and characteristics

oai_token-act-pair · gpt-3.5-turbo

expressions of emotional reactions and psychological states

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

)]

-0.74

cedented

-0.63

aughs

-0.60

cart

-0.58

TPPStreamerBot

-0.56

CVE

-0.55

EStream

-0.55

olen

-0.54

 disag

-0.54

audi

-0.54

POSITIVE LOGITS

 your

1.82

your

1.78

you

1.72

Your

1.63

 YOUR

1.62

 Your

1.59

 yourself

1.58

you

1.55

YOU

1.48

You

1.45

Activations Density 0.791%

adjectives and nouns related to personal attributes and characteristics

expressions of emotional reactions and psychological states

No Comments

No Known Activations