INDEX

Explanations

system-level keywords and elements from programming or technical content

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

Code snippets or programming-related content

np_acts-logits-general · gemini-2.0-flash

programming lessons and exercises

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

PRWEB

-0.51

 mapStateToProps

-0.50

ely

-0.46

Carriera

-0.45

эффици

-0.45

BASEPATH

-0.44

Trama

-0.44

flashdata

-0.44

"("

-0.44

dega

-0.43

POSITIVE LOGITS

 lesson

0.86

 exercise

0.83

 Exercise

0.82

Exercise

0.79

lesson

0.79

CWE

0.78

 practice

0.77

 Lesson

0.77

exercise

0.77

 exercises

0.73

Activations Density 0.368%

system-level keywords and elements from programming or technical content

Code snippets or programming-related content

programming lessons and exercises

No Comments

No Known Activations