INDEX

Explanations

phrases indicating a large quantity or amount

oai_token-act-pair · gpt-3.5-turbo

frequent mentions of the word "lot."

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

ESCO

-0.69

ħĭ

-0.62

gary

-0.59

merce

-0.59

deen

-0.57

 Mechdragon

-0.57

ufact

-0.57

inary

-0.57

gypt

-0.57

odan

-0.57

POSITIVE LOGITS

of

0.95

 happening

0.88

 riding

0.85

 going

0.79

 invested

0.72

 wrong

0.71

 else

0.71

 more

0.67

 accomplished

0.66

 crammed

0.66

Activations Density 0.051%

phrases indicating a large quantity or amount

frequent mentions of the word "lot."

No Comments

No Known Activations