INDEX

Explanations

special characters and formatting related to coding or programming syntax

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

code comments

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

 arşivlendi

-0.88

 queſta

-0.88

ſcher

-0.87

pecabe

-0.84

InputBorder

-0.83

хьтан

-0.82

parsedMessage

-0.82

ſchaft

-0.81

ſſung

-0.81

ésultats

-0.79

POSITIVE LOGITS

/*

0.52

↵

0.47

 <<<<<<<<<<<<<<

0.45

//

0.40

\[

0.38

<tr>

0.38

"""

0.36

0.35

################

0.35

Activations Density 0.004%

special characters and formatting related to coding or programming syntax

code comments

No Comments

No Known Activations