INDEX

Explanations

frequency of languages or linguistic phenomena in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

WebVitals

-0.64

 purpoſe

-0.63

 InputDecoration

-0.62

PerformLayout

-0.62

 houſe

-0.61

 calendriers

-0.61

 lenker

-0.56

 perſon

-0.56

 Профиль

-0.55

 Wicidata

-0.55

POSITIVE LOGITS

0.81

0.72

0.67

цездатний

0.59

abetes

0.56

ofold

0.53

 reprinted

0.52

 republished

0.52

tificate

0.51

haviour

0.51

Activations Density 0.126%

frequency of languages or linguistic phenomena in various contexts

No Comments

No Known Activations