INDEX

Explanations

terms related to advice on writing and responding to questions effectively

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.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

 مرئيه

-0.63

Geplaatst

-0.63

الإنجليزية

-0.61

دانشنامهٔ

-0.56

expandindo

-0.56

 transférez

-0.54

 Meksiku

-0.54

 imprimée

-0.53

EndInit

-0.52

 snippetHide

-0.51

POSITIVE LOGITS

-------------</

0.57

 كومونز

0.53

eux

0.53

Personensuche

0.52

 BoxFit

0.52

medriver

0.52

underbrace

0.49

lético

0.49

 FontWeight

0.49

TProtocol

0.49

Activations Density 1.145%

terms related to advice on writing and responding to questions effectively

No Comments

No Known Activations