INDEX

Explanations

phrases including "a way of", "a means of", or "a sign of".

oai_token-act-pair · gemini-2.0-flash

Method, approach

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 дописавши

-0.94

+#+#

-0.71

Спољашње

-0.61

 يتيمه

-0.59

WireFormatLite

-0.58

Datuak

-0.58

numerusform

-0.57

Diwedd

-0.57

ownic

-0.56

LookAnd

-0.54

POSITIVE LOGITS

addGap

0.62

<bos>

0.61

 trataba

0.56

 ↓,

0.54

 MonoBehaviour

0.54

 OnInit

0.52

 ploy

0.50

מנות

0.50

imed

0.49

addPreferredGap

0.49

Activations Density 1.021%

phrases including "a way of", "a means of", or "a sign of".

Method, approach

No Comments

No Known Activations