INDEX

Explanations

class and function definitions related to coding structures and properties

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

programming construct initializations or configurations

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

 Biôgrafia

-0.73

IUrlHelper

-0.70

SequentialGroup

-0.68

ьаж

-0.68

IntoConstraints

-0.66

RTGC

-0.65

OGND

-0.65

TryDecodeAsNil

-0.65

 Савезне

-0.65

ResumeLayout

-0.65

POSITIVE LOGITS

 Heimat

0.42

bob

0.36

insatz

0.33

MouseAdapter

0.32

ội

0.31

 Sitz

0.30

<blockquote>

0.30

ള

0.30

insten

0.30

ToProps

0.29

Activations Density 0.109%

class and function definitions related to coding structures and properties

programming construct initializations or configurations

No Comments

No Known Activations