INDEX

Explanations

elements related to logging and testing code structures

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

Code snippets or code-related text

np_acts-logits-general · gemini-2.0-flash

logging and technical terms

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

 <=",

-0.56

Demografie

-0.51

MigrationBuilder

-0.50

FormTagHelper

-0.49

 buster

-0.48

 AssemblyTitle

-0.48

jspx

-0.48

 contigo

-0.48

تقاوى

-0.47

 Buster

-0.46

POSITIVE LOGITS

+#+

0.76

MLLoader

0.68

AndEndTag

0.66

0.63

 كومونز

0.60

#+#

0.57

WireFormatLite

0.50

 getLayout

0.49

chien

0.48

Serv

0.48

Activations Density 0.121%

elements related to logging and testing code structures

Code snippets or code-related text

logging and technical terms

No Comments

No Known Activations