INDEX

Explanations

programming and include directives in code

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

code includes and paths

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

Personendaten

-0.62

reportWebVitals

-0.62

ReusableCell

-0.49

<?

-0.48

पया

-0.46

 informée

-0.46

pushFollow

-0.45

fromnode

-0.45



-0.45

 pleaſure

-0.45

POSITIVE LOGITS

rook

0.52

 diagonal

0.52

Pry

0.50

Hyd

0.50

ilda

0.50

ult

0.49

 Interchange

0.48

 extra

0.48

ecycle

0.47

 interchange

0.47

Activations Density 0.001%

programming and include directives in code

code includes and paths

No Comments

No Known Activations