INDEX

Explanations

function definitions in programming code

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

start of code execution

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

 wikipagina

-0.81

 ब्रेकडाउन

-0.63

 незавершена

-0.61

outSlope

-0.60

 Comprometido

-0.60

EDEFAULT

-0.60

DeleteBehavior

-0.58

LEncoder

-0.57

 judíos

-0.57

Filmographie

-0.56

POSITIVE LOGITS

__":

0.60

__':

0.43

 للاسماء

0.34

 NgModule

0.32

 wach

0.32

Bon

0.31

 dran

0.30

Cra

0.30

zit

0.30

Activations Density 0.001%

function definitions in programming code

start of code execution

No Comments

No Known Activations