INDEX

Explanations

metadata structures or elements in programming languages

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

Code-related text or symbols

np_acts-logits-general · gemini-2.0-flash

this source

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 MainAxisSize

-0.54

cipitation

-0.47

વે

-0.44

bootstrap

-0.43

 stehenden

-0.42

淋

-0.42

-0.41

 zero

-0.41

zonego

-0.41

łop

-0.40

POSITIVE LOGITS

 Савезне

0.77

contentLoaded

0.73

 AssemblyCulture

0.71

 للمعارف

0.71

 disambiguazione

0.69

RegressionTest

0.69

MockMvc

0.67

matchCondition

0.65

ValueStyle

0.65

]--;

0.65

Activations Density 0.153%

metadata structures or elements in programming languages

Code-related text or symbols

this source

No Comments

No Known Activations