INDEX

Explanations

references to software applications and their functionalities

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

LaTeX math formulas

np_acts-logits-general · gemini-2.0-flash

"$ or } after activating token

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 Roskov

-0.96

Diweddarwch

-0.92

expandindo

-0.90

 виправивши

-0.82

InvalidProtocol

-0.81

LookAnd

-0.80

IVEREF

-0.77

setVerticalGroup

-0.77

 <=",

-0.75

<eos>

-0.73

POSITIVE LOGITS

</em>

1.05

</i>

0.82

</u>

0.59

 einerseits

0.55

 وتسجيلات

0.53

 怎样

0.51

بوابة

0.51

中略

0.50

</h5>

0.48

ConstraintMaker

0.48

Activations Density 0.322%

references to software applications and their functionalities

LaTeX math formulas

"$ or } after activating token

No Comments

No Known Activations