INDEX

Explanations

programming structure elements and parameters in code snippets

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

TR/TE and image parameters

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

ſelf

-0.47

 suffixes

-0.44

pended

-0.43

ItemBackground

-0.43

EDEFAULT

-0.42

AddAttribute

-0.42

turno

-0.41

 thêm

-0.40

undial

-0.40

Życiorys

-0.40

POSITIVE LOGITS

ContentLoaded

0.50

AutoScaleMode

0.49

DockStyle

0.48

 same

0.44

 становника

0.42

GoogleApiClient

0.41

 мәкал

0.40

同样

0.39

 culture

0.38

 Kais

0.38

Activations Density 0.124%

programming structure elements and parameters in code snippets

TR/TE and image parameters

No Comments

No Known Activations