INDEX

Explanations

technical terms and quantifiable measures related to scientific methodologies and results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

出版年

-0.42

UnusedPrivate

-0.41

 protoimpl

-0.41

-0.40

̍t

-0.40

ÇA

-0.38

PreferredItem

-0.38

ത്

-0.38

⁡

-0.38

 showcased

-0.36

POSITIVE LOGITS

SaveVideo

0.54

 pauvreté

0.52

onOptions

0.49

StoryboardSegue

0.49

UrlResolution

0.47

OGND

0.47

 kiệm

0.45

 للاسماء

0.44

TabIndex

0.43

tablename

0.43

Activations Density 0.169%

technical terms and quantifiable measures related to scientific methodologies and results

No Comments

No Known Activations