INDEX

Explanations

punctuation marks and delimiters in structured data

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

references with numbers

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

 Мексичка

-0.71

PhysRevD

-0.63

astéro

-0.63

 esternos

-0.60

TagMode

-0.58

تقاوى

-0.57

 esterni

-0.57

postIndex

-0.56

setViewportView

-0.55

 increí

-0.53

POSITIVE LOGITS

↵

0.55

fromnode

0.54

 betweenstory

0.49

<strong>

0.43

0.40

{@

0.39

 Schmid

0.39

0.38

Activations Density 0.054%

punctuation marks and delimiters in structured data

references with numbers

No Comments

No Known Activations