INDEX

Explanations

mathematical definitions and theorems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

脚注の使い方

-0.59

 tartalomajánló

-0.56

PreferredItem

-0.55

 THEM

-0.53

прочем

-0.52

 userSchema

-0.51

 Respons

-0.50

amb

-0.48

 cont

-0.48

期刊论文

-0.47

POSITIVE LOGITS

 cathédrale

0.66

 vacunas

0.63

 église

0.62

 esistono

0.61

 direta

0.59

 mergeFrom

0.59

 ecran

0.58

 Infórmanos

0.58

 közül

0.56

 disambiguazione

0.56

Activations Density 1.366%

mathematical definitions and theorems

No Comments

No Known Activations