INDEX

Explanations

references to scientific studies and evidence

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

GOTREF

-0.65

Slf

-0.57

 Jefus

-0.55

tainen

-0.53

 traseiro

-0.53

 recomendo

-0.49

 pleaſure

-0.49

NOPQRST

-0.48

 profundas

-0.48

$_"

-0.48

POSITIVE LOGITS

 lenker

0.84

ьаж

0.74

findpost

0.72

queryInterface

0.71

 Roskov

0.71

Autoritní

0.69

MessageOf

0.66

참고

0.66

contentLoaded

0.63

Aholisi

0.62

Activations Density 0.159%

references to scientific studies and evidence

No Comments

No Known Activations