INDEX

Explanations

code-related terms and keywords associated with JavaScript and programming concepts

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

Tokens before numbers or after conjunctions

np_acts-logits-general · gemini-2.0-flash

será retornado, ser lido

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

awtextra

-0.80

InSection

-0.79

ⓧ

-0.77

principalColumn

-0.75

 AssemblyProduct

-0.73

BeginContext

-0.72

Démographie

-0.71

 TextAppearance

-0.69

GraphicsUnit

-0.69

ISupport

-0.68

POSITIVE LOGITS

 most

0.50

hal

0.46

 яку

0.45

itself

0.43

 implementa

0.43

Posted

0.42

anadas

0.42

 itself

0.41

himself

0.41

andinavian

0.40

Activations Density 0.033%

code-related terms and keywords associated with JavaScript and programming concepts

Tokens before numbers or after conjunctions

será retornado, ser lido

No Comments

No Known Activations