INDEX

Explanations

mathematical notation and symbols related to functions and topology

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

Datuak

-0.64

 tartalomajánló

-0.61

)++;

-0.58

RegistryLite

-0.56

 ujednoznacz

-0.55

oprot

-0.55

 bezeichneter

-0.54

 zufolge

-0.54

}{*}{

-0.53

"]="

-0.53

POSITIVE LOGITS

0.79

0.69

mid

0.61

 betweenstory

0.61

0.55

｜

0.55

∣

0.54

kost

0.52

│

0.51

│

0.50

Activations Density 0.445%

mathematical notation and symbols related to functions and topology

No Comments

No Known Activations