INDEX

Explanations

terms related to data structures and programming constructs

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

auto bed leveling

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

 المعيارى

-0.59

 صوتيه

-0.56

AddHtmlAttribute

-0.52

alibaba

-0.42

yyj

-0.41

 препратки

-0.41

 powers

-0.40

zed

-0.40

السكان

-0.39

 UIAlert

-0.39

POSITIVE LOGITS

ніципалі

0.50

IUrlHelper

0.46

DispatchToProps

0.43

ContentAsync

0.42

writeField

0.41

 HttpNotFound

0.41

𝟶

0.40

frc

0.38

horabuena

0.37

verifyException

0.35

Activations Density 1.694%

terms related to data structures and programming constructs

auto bed leveling

No Comments

No Known Activations