INDEX

Explanations

code-related syntax elements and function calls

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

coordinates and position

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

principalTable

-0.73

 tartalomajánló

-0.70

 المعيارى

-0.68

 '\\;'

-0.68

 autorytatywna

-0.67

脚注の使い方

-0.66

ſelben

-0.66

 queſta

-0.66

NgModule

-0.65

 DialogInterface

-0.65

POSITIVE LOGITS

 location

0.60

IntoConstraints

0.51

 position

0.48

Location

0.48

 LOCATION

0.47

 Location

0.45

位置

0.44

location

0.43

 locations

0.42

 ubicación

0.40

Activations Density 0.056%

code-related syntax elements and function calls

coordinates and position

No Comments

No Known Activations