INDEX

Explanations

partial bits of code or HTML, as well as the word "loading" and "continue reading"

oai_token-act-pair · gemini-2.0-flash

words or phrases related to loading data or search operations

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

Webpage loading/display

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

migrationBuilder

-0.84

 चीज़ों

-0.65

featureID

-0.65

UserScript

-0.62

}">

-0.61

Географиясе

-0.61

DoubleQuotes

-0.60

 "..\..\..\

-0.60

XMLSchema

-0.59

 fieldNum

-0.59

POSITIVE LOGITS

acağına

0.43

Rüyada

0.42

 register

0.39

 registrados

0.38

த்தில்

0.37

Register

0.37

RegressionTest

0.37

全

0.37

基

0.36

Gambas

0.36

Activations Density 0.234%

partial bits of code or HTML, as well as the word "loading" and "continue reading"

words or phrases related to loading data or search operations

Webpage loading/display

No Comments

No Known Activations