INDEX

Explanations

code syntax and structure related to programming logic

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

Assignment operator (=)

np_acts-logits-general · gemini-2.0-flash

new object instantiation

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

mido

-0.47

úng

-0.45

 hwnd

-0.45

 balsam

-0.43

 CGSize

-0.42

pushButton

-0.42

[`

-0.42

 onResume

-0.41

&[

-0.41

[],

-0.41

POSITIVE LOGITS

new

0.84

Хьажоргаш

0.80

new

0.80

はじめに

0.74

帖最后由

0.72

참고

0.66

TestTools

0.66

ɵɵ

0.66

исленность

0.65

 nuovi

0.65

Activations Density 0.048%

code syntax and structure related to programming logic

Assignment operator (=)

new object instantiation

No Comments

No Known Activations