INDEX

Explanations

quantifiable measures of work experience and duration in a specific field

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

DataAnnotations

-0.50

bè

-0.37

sätzlich

-0.35

 synes

-0.35

Vendo

-0.34

ArgumentParser

-0.34

mulos

-0.33

 sáng

-0.33

EndContext

-0.33

Charset

-0.33

POSITIVE LOGITS

 pinulongan

0.60

經驗

0.59

experience

0.58

adaptiveStyles

0.57

experienced

0.57

 experien

0.55

 EXPERIENCE

0.55

经验

0.55

 experience

0.54

 experienced

0.54

Activations Density 0.035%

quantifiable measures of work experience and duration in a specific field

No Comments

No Known Activations