INDEX

Explanations

references to awards and recognitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

Aktualisiert

-0.55

parsedMessage

-0.52

RuleContext

-0.51

GEBURTSDATUM

-0.48

 fieldNum

-0.48

 AssemblyCulture

-0.47

SetString

-0.44

KURZBESCHREIBUNG

-0.42

Життєпис

-0.41

Vors

-0.41

POSITIVE LOGITS

 awards

0.60

 accolades

0.56

 award

0.54

awards

0.52

 recogni

0.52

 awarded

0.47

 Awards

0.47

 received

0.47

Award

0.46

award

0.46

Activations Density 0.306%

references to awards and recognitions

No Comments

No Known Activations