INDEX

Explanations

capitalized proper names

oai_token-act-pair · gemini-2.0-flash

technical terms and names in documentation

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

Legal names in court records

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Revenir

-0.66

={({

-0.57

 fubject

-0.55

بوابة

-0.51

 propOrder

-0.50

ksin

-0.49

AccessorTable

-0.49

<?

-0.49

ThroughAttribute

-0.48

stateProvider

-0.47

POSITIVE LOGITS

UnusedPrivate

0.69

WriteTagHelper

0.59

webElementXpaths

0.55

NewUrlParser

0.54

colgroup

0.54

 ComVisible

0.50

elemField

0.48

bolista

0.48

BitmapFactory

0.48

Carriera

0.47

Activations Density 1.184%

capitalized proper names

technical terms and names in documentation

Legal names in court records

No Comments

No Known Activations