INDEX

Explanations

questions that start with "What is."

oai_token-act-pair · gpt-3.5-turbo

questions or interrogative phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 manif

-0.71

 marsh

-0.69

 binge

-0.68

 encount

-0.66

 normalized

-0.66

 healed

-0.66

 mutually

-0.66

 labor

-0.66

 colon

-0.66

 slam

-0.66

POSITIVE LOGITS

[/

1.00

 Improve

0.95

 Nope

0.95

Â¶

0.94

 Where

0.93

 Anyone

0.91

Why

0.88

 Yourself

0.88

 Seriously

0.86

 Answer

0.86

Activations Density 0.099%

questions that start with "What is."

questions or interrogative phrases

No Comments

No Known Activations