INDEX

Explanations

specific technical terms and identifiers related to programming and data structures

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

Shapes and structures

np_acts-logits-general · gemini-2.0-flash

geometric shapes and structures

np_acts-logits-general · gemini-2.5-flash-lite

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

!*\

-0.78

 ModelExpression

-0.62

帖最后由

-0.60

TestingModule

-0.59

BindView

-0.56

InvalidProtocol

-0.55

Personensuche

-0.54

ContentAsync

-0.52

richTextPanel

-0.52

навли

-0.51

POSITIVE LOGITS

 shaped

1.11

 shape

1.04

shaped

1.03

haped

0.98

形

0.91

 Shaped

0.89

状

0.81

shape

0.81

形の

0.81

 structure

0.79

Activations Density 0.990%

specific technical terms and identifiers related to programming and data structures

Shapes and structures

geometric shapes and structures

No Comments

No Known Activations