INDEX

Explanations

terms related to academic analysis and information assessment

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

LookAnd

-1.09

contentLoaded

-0.88

UrlResolution

-0.72

GEBURTSDATUM

-0.71

 resourceCulture

-0.68

IndentedString

-0.67

ValueStyle

-0.66

parsedMessage

-0.65

GEBURTS

-0.64

oa̍t

-0.63

POSITIVE LOGITS

 magis

0.40

 ſch

0.39

 Houſe

0.37

0.35

 تخصصی

0.35

 oock

0.35

<?

0.34

----------

0.34

 againſt

0.33

 ſub

0.33

Activations Density 1.164%

terms related to academic analysis and information assessment

No Comments

No Known Activations