INDEX

Explanations

words related to asking questions, coding, scientific processes, or life comparisons

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

DockStyle

-0.63

UnusedPrivate

-0.56

webElementXpaths

-0.53

ThemeOverlay

-0.53

 Chriftian

-0.52

lineno

-0.52

 neceff

-0.50

 jsPsych

-0.48

 caufe

-0.48

 Rumuni

-0.47

POSITIVE LOGITS

LEncoder

0.71

ContentAsync

0.69

 correctes

0.68

URLException

0.62

peteer

0.61

URIComponent

0.58

strdup

0.55

Amicalement

0.55

espejo

0.53

numberOfLines

0.53

Activations Density 31.101%

words related to asking questions, coding, scientific processes, or life comparisons

No Comments

No Known Activations