INDEX

Explanations

programming constructs and keywords related to variable declarations and function definitions

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

AST node classification

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

webElementXpaths

-0.58

RuleContext

-0.50

fromnode

-0.50

}-*/;

-0.49

 betweenstory

-0.48

AutoresizingMask

-0.46

➟

-0.46

oa̍t

-0.45

 Chwiliwch

-0.43

Према

-0.40

POSITIVE LOGITS

inander

0.44

 لينك

0.43

ildes

0.42

 HttpNotFound

0.41

 فريبيس

0.41

 adsorption

0.40

 חיצוניים

0.40

 Erfindung

0.40

chtest

0.40

 tracción

0.39

Activations Density 0.036%

programming constructs and keywords related to variable declarations and function definitions

AST node classification

No Comments

No Known Activations