INDEX

Explanations

references to programming concepts and code elements

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

Abbreviations and shortened words

np_acts-logits-general · gemini-2.0-flash

triumf OR Simple RegressionTest OR ict OR st OR t OR ms OR Shri OR s OR An OR It

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

tagHelperRunner

-1.07

 BoxDecoration

-0.97

 ―――――

-0.97

RectangleBorder

-0.97

 itſelf

-0.96

EndInit

-0.95

Personendaten

-0.95

Efq

-0.95

 myſelf

-0.94

 дописавши

-0.94

POSITIVE LOGITS

0.58

fore

0.56

0.55

0.54

set

0.53

Activations Density 0.384%

references to programming concepts and code elements

Abbreviations and shortened words

triumf OR Simple RegressionTest OR ict OR st OR t OR ms OR Shri OR s OR An OR It

No Comments

No Known Activations