INDEX

Explanations

brands and companies

oai_token-act-pair · gpt-3.5-turbo

mentions of specific brands or products

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

 Canaver

-0.53

>]

-0.49

 THESE

-0.47

 distinctly

-0.46

":[{"

-0.46

ËĪ

-0.45

agame

-0.45

apixel

-0.45

Welcome

-0.45

Below

-0.44

POSITIVE LOGITS

etc

1.13

!,

0.91

,...

0.87

*,

0.82

?,

0.81

+,

0.80

Â®,

0.78

,,

0.70

,[

0.66

Activations Density 0.697%

brands and companies

mentions of specific brands or products

No Comments

No Known Activations