INDEX

Explanations

code-related terms and structures, specifically related to programming functions and data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

usercontent

-0.57

marle

-0.57

esticular

-0.56

UIControlState

-0.53

TRIBUTE

-0.52

τού

-0.52

 infatti

-0.49

onais

-0.49

umerate

-0.48

math

-0.47

POSITIVE LOGITS

 HasFactory

0.58

oplayer

0.57

 '\\;'

0.56

ьаж

0.55

 ivelany

0.52

 فريبيس

0.51

 ویکی‌پدیای

0.50

 pinulongan

0.50

 intStringLen

0.50

isContained

0.49

Activations Density 0.090%

code-related terms and structures, specifically related to programming functions and data structures

No Comments

No Known Activations