INDEX

Explanations

structured data or references in a technical context

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

maps, categories, descriptions, programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

WriteTagHelper

-0.75

 JpaRepository

-0.72

GOTREF

-0.70

#+#

-0.69

 MainAxisSize

-0.61

 InputDecoration

-0.60

 تضيفلها

-0.60

HXLINE

-0.59

SharedCtor

-0.58

şört

-0.57

POSITIVE LOGITS

rawDesc

0.48

mml

0.35

 logo

0.35

igg

0.35

=========

0.34

Tor

0.34

си

0.34

 estri

0.33

 Pell

0.33

 Bari

0.32

Activations Density 0.007%

structured data or references in a technical context

maps, categories, descriptions, programming

No Comments

No Known Activations