INDEX

Explanations

numerical values or data points

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

Numbers

np_acts-logits-general · gemini-2.0-flash

numbers and dates

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

httphttps

-0.61

BSITE

-0.55

brities

-0.54

 ويكيپيديا

-0.54

vestream

-0.54

dreamstime

-0.53

Lähteet

-0.52

 iVar

-0.52

 deciso

-0.51

人で

-0.51

POSITIVE LOGITS

 ―――――

0.77

erb

0.71

 Boven

0.69

 useAuth

0.68

 itſelf

0.68

%)$

0.66

السكان

0.64

 AssemblyTitle

0.63

DataAnnotations

0.63

 ་་

0.63

Activations Density 0.363%

numerical values or data points

Numbers

numbers and dates

No Comments

No Known Activations