INDEX

Explanations

expressions related to following rules and regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/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.10.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

点头

-0.40

<bos>

-0.39

[++

-0.39

weit

-0.38

mej

-0.37

fahr

-0.37

双眼

-0.37

कि

-0.36

IVES

-0.36

 comigo

-0.36

POSITIVE LOGITS

 EconPapers

0.88

GEBURTSDATUM

0.80

ScopeManager

0.77

ContentAsync

0.77

цездатний

0.76

 iyon

0.75

 photolibrary

0.75

 iſt

0.73

 ་་

0.72

 thereof

0.71

Activations Density 1.248%

expressions related to following rules and regulations

No Comments

No Known Activations