INDEX

Explanations

constructions and keywords typically associated with database queries and programming logic

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

code snippets and programming syntax

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

 Umum

-0.47

 Kebijakan

-0.45

NOUNC

-0.45

 reported

-0.41

wantErr

-0.40

 pungkas

-0.40

reported

-0.39

翻攝

-0.38

zehn

-0.37

 Bahkan

-0.37

POSITIVE LOGITS

setVerticalGroup

0.77

 Савезне

0.53

HtmlAttribute

0.53

]=>

0.52

TagMode

0.52

SharedCtor

0.49

SPJ

0.48

 FetchType

0.46

EndGlobalSection

0.46

SharedDtor

0.45

Activations Density 0.004%

constructions and keywords typically associated with database queries and programming logic

code snippets and programming syntax

No Comments

No Known Activations