INDEX

Explanations

phrases that include the words "including" or "especially" to highlight specific entities within a larger group

oai_token-act-pair · gpt-3.5-turbo

references to inclusion and participation in various contexts

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

bis

-0.78

ript

-0.72

ielding

-0.68

ahime

-0.68

ibilities

-0.67

ossession

-0.66

ciation

-0.66

ioxide

-0.66

erred

-0.65

Features

-0.64

POSITIVE LOGITS

 myself

1.33

 ourselves

1.11

 journalists

1.07

 yourselves

1.04

 oneself

1.03

 clergy

1.02

 politicians

1.02

 celebrities

1.01

 feminists

1.00

 strangers

1.00

Activations Density 0.237%

phrases that include the words "including" or "especially" to highlight specific entities within a larger group

references to inclusion and participation in various contexts

No Comments

No Known Activations