INDEX

Explanations

the word "front" or phrases including it

oai_token-act-pair · gemini-2.0-flash

words related to front-end development

np_token-act-pair-logits · gpt-4o-mini

front

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 fallu

-0.68

 okuyayım

-0.64

 صوتيه

-0.61

roffene

-0.59

gdx

-0.58

UserScript

-0.58

 varargin

-0.57

WebServlet

-0.56

vespa

-0.56

 Purg

-0.56

POSITIVE LOGITS

ha

0.56

EndProject

0.51

 Counter

0.51

sal

0.50

Hä

0.50

InputBorder

0.50

不及

0.49

Counter

0.49

counter

0.48

row

0.47

Activations Density 0.389%

the word "front" or phrases including it

words related to front-end development

front

No Comments

No Known Activations