INDEX

Explanations

references to configuration settings and attributes in code or documentation

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

Tokens preceding file extensions or delimiters

np_acts-logits-general · gemini-2.0-flash

configuration settings

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

Билгалдахарш

-0.54

 getItemId

-0.49

enterOuterAlt

-0.45

 NavController

-0.45

 يتيمه

-0.44

Diwedd

-0.43

 ProtoMessage

-0.42

protoimpl

-0.41

findpost

-0.41

المكان

-0.41

POSITIVE LOGITS

SharedCtor

0.55

 settings

0.49

 preferences

0.48

 configuration

0.48

 config

0.48

styleable

0.48

 parameters

0.46

 provisions

0.45

配置

0.44

config

0.44

Activations Density 0.402%

references to configuration settings and attributes in code or documentation

Tokens preceding file extensions or delimiters

configuration settings

No Comments

No Known Activations