INDEX

Explanations

references to user interface elements and toolbars in programming contexts

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

toolbar and bars

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

ValueStyle

-0.60

OCCURRED

-0.51

isEmail

-0.50

WritableDatabase

-0.47

ETHING

-0.44

рого

-0.43

Biografia

-0.43

glVertex

-0.42

encodeWith

-0.42

modelBuilder

-0.42

POSITIVE LOGITS

 onOptions

0.47

OptionsMenu

0.47

XtraBars

0.47

btns

0.46

 buttons

0.46

 nástro

0.45

+#+#

0.44

LookAnd

0.44

toolbar

0.44

 externi

0.43

Activations Density 0.012%

references to user interface elements and toolbars in programming contexts

toolbar and bars

No Comments

No Known Activations