INDEX

Explanations

code structures, specifically function definitions and control flow elements

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

Code snippets and programming syntax

np_acts-logits-general · gemini-2.0-flash

user input leading to code execution

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

fjspx

-0.65

 oprot

-0.64

########.

-0.62

CppMethod

-0.60

rungsseite

-0.60

avigation

-0.58

 Administrativna

-0.58

Autoritní

-0.58

 Geſch

-0.57

 Italijanski

-0.57

POSITIVE LOGITS

 actionPerformed

0.39

stop

0.32

subsubsection

0.31

illoin

0.30

 inmedi

0.30

EventHandler

0.29

 okam

0.28

CM

0.28

do

0.28

WithIdentifier

0.27

Activations Density 0.140%

code structures, specifically function definitions and control flow elements

Code snippets and programming syntax

user input leading to code execution

No Comments

No Known Activations