INDEX

Explanations

terms related to imaging techniques and biological processes, such as staining, localization, and receptors

oai_token-act-pair · gpt-3.5-turbo

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

Kids

-0.75

TextColor

-0.72

 sprawling

-0.70

iquette

-0.69

 perks

-0.69

Cola

-0.68

partisan

-0.66

Disney

-0.66

 Citizen

-0.66

 daddy

-0.64

POSITIVE LOGITS

().

1.22

 âĪ¼

1.21

(<

1.11

(>

1.11

 (âĪĴ

1.08

 assay

1.07

 characterized

1.04

([

0.99

(),

0.98

 observed

0.97

Activations Density 0.617%

terms related to imaging techniques and biological processes, such as staining, localization, and receptors

No Comments

No Known Activations