INDEX

Explanations

programming syntax and structure related to function definitions and data types

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

JfrSymbolId::mark(with leakp)

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

IntoConstraints

-0.40

ceps

-0.39

().__

-0.37

mnop

-0.35

ValueGeneration

-0.35

期刊论文

-0.34

lossians

-0.34

hyrchwyd

-0.33

GEBURTSDATUM

-0.33

Források

-0.32

POSITIVE LOGITS

 betweenstory

0.53

RegressionTest

0.48

WebElementEntity

0.44

writeFieldEnd

0.44

MergeFrom

0.44

IndentedString

0.43

ValueStyle

0.43

IUrlHelper

0.42

 Taktlose

0.42

SuspendLayout

0.41

Activations Density 0.171%

programming syntax and structure related to function definitions and data types

JfrSymbolId::mark(with leakp)

No Comments

No Known Activations