INDEX

Explanations

references to individuals and their characteristics or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 désolés

-0.53

 dukungan

-0.52

 femininas

-0.51

Autoritní

-0.49

 supplé

-0.49

writeFieldEnd

-0.48

UnitTesting

-0.47

 lettore

-0.47

 soutien

-0.47

 penjelasan

-0.47

POSITIVE LOGITS

 fuckin

0.71

guy

0.68

 fucking

0.68

 bastards

0.65

 freakin

0.62

 fella

0.60

 crap

0.60

 damn

0.60

 freaking

0.59

 goddamn

0.59

Activations Density 0.141%

references to individuals and their characteristics or actions

No Comments

No Known Activations