INDEX

Explanations

references to signs and their characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ObjectContext

-0.64

раздо

-0.58

出版年

-0.56

 trebui

-0.55

setCellStyle

-0.55

genomen

-0.55

 Dasar

-0.52

AdapterView

-0.51

udah

-0.51

 tölt

-0.50

POSITIVE LOGITS

 signage

1.02

 Signage

0.95

 signs

0.82

 sign

0.79

 Signs

0.76

 placard

0.71

 billboard

0.69

 mural

0.66

 display

0.65

 billboards

0.65

Activations Density 0.201%

references to signs and their characteristics

No Comments

No Known Activations