INDEX

Explanations

phrases related to themes or main points in written content

oai_token-act-pair · gpt-3.5-turbo

discussions around values and principles in decision-making

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Judd

-0.67

 Jaguar

-0.64

 unanim

-0.64

Jeb

-0.63

CBS

-0.63

JPM

-0.63

 Vera

-0.63

 Revision

-0.62

 confirmed

-0.62

 Zimmerman

-0.62

POSITIVE LOGITS

asuring

0.85

otion

0.81

ãĤ¹

0.78

 empowering

0.76

irection

0.72

otional

0.72

porate

0.71

iving

0.70

TYPE

0.70

centered

0.69

Activations Density 0.512%

phrases related to themes or main points in written content

discussions around values and principles in decision-making

No Comments

No Known Activations