INDEX

Explanations

database schema definitions and variable types

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

تقاوى

-0.69

 समीक्षाओं

-0.59

#+#

-0.56

("}");

-0.56

 Савезне

-0.56

tanleria

-0.55

 Administrativna

-0.54

出版年

-0.53

RefNanny

-0.53

aarrggbb

-0.53

POSITIVE LOGITS

BeginContext

0.72

 maxLength

0.66

IntoConstraints

0.65

<bos>

0.60

 characters

0.59

长度

0.58

length

0.57

 length

0.57

HasMaxLength

0.54

characters

0.53

Activations Density 0.069%

database schema definitions and variable types

No Comments

No Known Activations