INDEX

Explanations

technical specifications and updates in programming contexts

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

version, technology, and updates

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

ChildScrollView

-0.63

RenderAtEndOf

-0.59

 InputDecoration

-0.59

BEM

-0.56

AnchorTagHelper

-0.56

MethodManager

-0.56

extAlignment

-0.54

SequentialGroup

-0.53

centralwidget

-0.52

ArgsConstructor

-0.52

POSITIVE LOGITS

OrNil

0.45

 Tecnología

0.38

 versiones

0.38

version

0.37

 version

0.37

 sür

0.37

 tecnología

0.36

 modernos

0.36

Version

0.35

 adquis

0.35

Activations Density 0.078%

technical specifications and updates in programming contexts

version, technology, and updates

No Comments

No Known Activations