INDEX

Explanations

variable assignments and manipulations

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

loop iterators and code structures

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

iſen

-0.66

OGND

-0.66

 Мексичка

-0.65

 Chwiliwch

-0.62

Демографія

-0.61

 MainAxisSize

-0.60

 AssemblyCulture

-0.60

IUrlHelper

-0.59

IntoConstraints

-0.59

WebVitals

-0.57

POSITIVE LOGITS

 entier

0.35

 répertoire

0.33

當初

0.33

rotnie

0.32

strtolower

0.32

út

0.31

žo

0.31

หน้านี้

0.31

 person

0.31

 Concern

0.31

Activations Density 0.054%

variable assignments and manipulations

loop iterators and code structures

No Comments

No Known Activations