INDEX

Explanations

debugging and logging related terms

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

programming code snippets

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

 tenisky

-0.47

 createState

-0.46

wieś

-0.45

 ancla

-0.41

SuspendLayout

-0.41

 oseb

-0.41

niversitesi

-0.41

 Reſ

-0.41

antaranya

-0.40

purl

-0.40

POSITIVE LOGITS

makeText

0.64

JspWriter

0.56

sweetalert

0.49

Hauptartikel

0.45

 UnityEngine

0.44

 println

0.43

 shouts

0.42

Cud

0.41

 UnityEditor

0.41

 Debug

0.41

Activations Density 0.001%

debugging and logging related terms

programming code snippets

No Comments

No Known Activations