INDEX

Explanations

references to specific numerical data and formatting patterns

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

Colons in file paths or time codes

np_acts-logits-general · gemini-2.0-flash

addition and expansion

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

 InputDecoration

-0.72

/**

-0.59

 BoxDecoration

-0.56

férés

-0.54

versiti

-0.51

 BorderRadius

-0.50

thof

-0.50

bersicht

-0.49

ंदीखरीदारी

-0.47

 חיצוניים

-0.47

POSITIVE LOGITS

 expansion

0.87

 Addition

0.87

 addition

0.86

 متعلقه

0.85

 extension

0.85

 expansions

0.84

 additions

0.83

Addition

0.83

 Expansion

0.81

addition

0.81

Activations Density 0.184%

references to specific numerical data and formatting patterns

Colons in file paths or time codes

addition and expansion

No Comments

No Known Activations