INDEX

Explanations

organizational acronyms and relevant academic references

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

Acronyms/initialisms

np_acts-logits-general · gemini-2.0-flash

acronyms and initialisms

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

Véxase

-0.55

vertra

-0.53

]),

-0.53

 defaultstate

-0.50

matchCondition

-0.50

 hObject

-0.49

ricus

-0.48

Koordinaten

-0.48

Източници

-0.48

 solution

-0.48

POSITIVE LOGITS

 betweenstory

0.61

DMR

0.59

 RSSSF

0.59

SRM

0.59

 jadx

0.58

 Faso

0.57

 Saxons

0.56

 photolibrary

0.56

SRT

0.56

SRA

0.55

Activations Density 1.272%

organizational acronyms and relevant academic references

Acronyms/initialisms

acronyms and initialisms

No Comments

No Known Activations