INDEX

Explanations

programming constructs related to data structures and type definitions

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

programming struct definitions

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

-------------</

-0.49

İstinadlar

-0.43

FailureListener

-0.41

contentPane

-0.37

 élevées

-0.37

AppComponent

-0.36

 battre

-0.36

 tampoco

-0.35

 iNdEx

-0.35

 HasFactory

-0.34

POSITIVE LOGITS

CppMethod

0.68

CreateModel

0.67

RTLI

0.60

WriteAttribute

0.60

dataclass

0.60

Personendaten

0.60

 &___

0.56

struct

0.56

setVerticalGroup

0.55

AddHtmlAttribute

0.54

Activations Density 0.007%

programming constructs related to data structures and type definitions

programming struct definitions

No Comments

No Known Activations