INDEX

Explanations

words related to eating or consuming

oai_token-act-pair · gpt-3.5-turbo

words related to food or eating

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

Constructed

-0.71

EMP

-0.68

USER

-0.68

SPONSORED

-0.67

 Stevenson

-0.66

 Divinity

-0.66

AUT

-0.65

åĬ

-0.65

RIPT

-0.65

Import

-0.64

POSITIVE LOGITS

bled

1.64

bles

1.63

bling

1.51

blers

1.44

ble

1.42

bler

1.23

bing

1.20

bly

1.19

bage

1.17

glers

1.11

Activations Density 0.132%

words related to eating or consuming

words related to food or eating

No Comments

No Known Activations