INDEX

Explanations

phrases indicating the beginning or introduction of a topic or article

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the speaker's perspective or personal involvement

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

 minds

-0.61

 lifestyles

-0.61

alore

-0.61

 Lives

-0.60

utic

-0.59

cedes

-0.58

Berry

-0.57

Alert

-0.57

 Wise

-0.56

 harms

-0.56

POSITIVE LOGITS

'm

1.05

 apologise

1.01

 apologize

0.98

 summarize

0.98

 briefly

0.89

 propose

0.89

 introduce

0.84

 reiterate

0.84

 reprint

0.81

 reproduce

0.80

Activations Density 0.330%

phrases indicating the beginning or introduction of a topic or article

phrases indicating the speaker's perspective or personal involvement

No Comments

No Known Activations