INDEX

Explanations

HTML or XML markup tags and their corresponding attributes

oai_token-act-pair · gpt-4o-mini Triggered by @bot

opening html tags

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

=$?

-0.59

️⃣

-0.52

 EventArgs

-0.51

المكان

-0.48

oredCriteria

-0.48

 ActionBar

-0.47

tangentMode

-0.46

providedIn

-0.45

ValueStyle

-0.45

RTEE

-0.45

POSITIVE LOGITS

 $('<

0.98

"<

0.96

("<

0.94

('<

0.92

 $("<

0.91

'<

0.90

'<

0.85

"<

0.82

="<

0.75

0.73

Activations Density 0.002%

HTML or XML markup tags and their corresponding attributes

opening html tags

No Comments

No Known Activations