INDEX

Explanations

phrases related to exerting force or pressure on someone or something to do something specific

oai_token-act-pair · gpt-3.5-turbo

instances of coercion or force affecting individuals or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

pport

-0.75

ording

-0.67

izoph

-0.65

effect

-0.59

ilyn

-0.59

padding

-0.54

 Wish

-0.54

demand

-0.54

pot

-0.53

 Conquer

-0.53

POSITIVE LOGITS

 into

1.36

 onto

1.24

into

1.16

 Into

1.07

 INTO

1.01

 ashore

0.94

 away

0.92

 overboard

0.87

out

0.87

to

0.85

Activations Density 0.216%

phrases related to exerting force or pressure on someone or something to do something specific

instances of coercion or force affecting individuals or groups

No Comments

No Known Activations