INDEX

Explanations

words related to improvements or enhancements showing up in a technical or analytical context

oai_token-act-pair · gpt-3.5-turbo

patterns related to human characteristics or attributes

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

 Mirage

-0.71

 Rhodes

-0.70

 Chattanooga

-0.68

 Reyn

-0.66

 Benny

-0.65

Nau

-0.65

 rumours

-0.64

 misunder

-0.64

 Baron

-0.64

 Jinn

-0.64

POSITIVE LOGITS

ï¸ı

1.07

âĶĢâĶĢâĶĢâĶĢ

0.98

selves

0.91

iors

0.90

 selves

0.88

Â¯Â¯

0.87

imately

0.84

xual

0.83

Â£

0.81

physical

0.80

Activations Density 0.327%

words related to improvements or enhancements showing up in a technical or analytical context

patterns related to human characteristics or attributes

No Comments

No Known Activations