INDEX

Explanations

function-related keywords and operations in code

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

Code snippets or program code

np_acts-logits-general · gemini-2.0-flash

layout alignment code

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GraphicsUnit

-0.63

ContentAsync

-0.61

енча

-0.59

henswürdigkeiten

-0.57

contentLoaded

-0.55

postmedia

-0.54

 Thirdly

-0.52

 فريبيس

-0.51

 Weltkrieg

-0.51

 المرجع

-0.49

POSITIVE LOGITS

ParallelGroup

1.13

SequentialGroup

0.70

CodedInputStream

0.67

 layout

0.65

Alignment

0.64

 layouts

0.61

Билгалдахарш

0.58

TRAILING

0.52

layout

0.52

findpost

0.52

Activations Density 0.025%

function-related keywords and operations in code

Code snippets or program code

layout alignment code

No Comments

No Known Activations