INDEX

Explanations

references to citations and sections in documents

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

section {number}

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

LookAnd

-0.75

msgTypes

-0.72

parsedMessage

-0.66

 Biôgrafia

-0.61

}$

-0.60

ThroughAttribute

-0.58

bonucleic

-0.58

posedge

-0.57

jspx

-0.56

SequentialGroup

-0.56

POSITIVE LOGITS

 Перейти

0.32

setAlignment

0.30

また

0.30

0.29

“

0.29

 heuti

0.27

{(

0.27

<td>

0.27

azen

0.27

mrow

0.26

Activations Density 0.000%

references to citations and sections in documents

section {number}

No Comments

No Known Activations

references to citations and sections in documents

section {number}

No Comments

No Known Activations