INDEX

Explanations

references to images or visuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

|')

-0.72

};*/

-0.67

IsMutable

-0.65

 '*')

-0.65

,:);

-0.64

вгений

-0.62

 numerus

-0.62

 Espanha

-0.62

 Hình

-0.61

 itemList

-0.59

POSITIVE LOGITS

 picture

1.02

 photo

0.90

picture

0.71

pic

0.67

 foto

0.58

photo

0.58

 상세

0.58

AutoField

0.57

 PICTURE

0.56

abestanden

0.55

Activations Density 0.115%

references to images or visuals

No Comments

No Known Activations