INDEX

Explanations

quantitative descriptors related to measurements and performance

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

maximum or best values

np_acts-logits-general · gemini-2.0-flash

highest values and results

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

基

-0.44

*>(

-0.44

 imageNamed

-0.43

 supaya

-0.43

ora

-0.42

 đủ

-0.41

 alapján

-0.40

os

-0.40

 basic

-0.40

itte

-0.39

POSITIVE LOGITS

 occurred

0.91

 occurs

0.86

 occur

0.81

occurs

0.79

 occured

0.76

 '\\;'

0.76

occur

0.76

TextAppearance

0.75

 ocur

0.71

 happened

0.71

Activations Density 0.440%

quantitative descriptors related to measurements and performance

maximum or best values

highest values and results

No Comments

No Known Activations