INDEX

Explanations

mentions of various web development technologies, especially HTML

oai_token-act-pair · gemini-2.0-flash

HTML-related terms

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

HTML

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

 betweenstory

-0.75

featureID

-0.64

脚注の使い方

-0.62

曖昧さ回避

-0.62

MigrationBuilder

-0.59

Portály

-0.58

ParallelGroup

-0.54

 onBind

-0.54

Espèce

-0.53

 виправивши

-0.53

POSITIVE LOGITS

AndroidJUnit

0.48

InstanceState

0.48

GIVEREF

0.48

findpost

0.47

GeneratedMessage

0.46

UrlResolution

0.45

 modello

0.45

endront

0.44

WriteBarrier

0.43

Activations Density 1.474%

mentions of various web development technologies, especially HTML

HTML-related terms

HTML

No Comments

No Known Activations