INDEX

Explanations

references to specific characteristics and specifications, particularly in a scientific or technical context

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 betweenstory

-0.82

WriteTagHelper

-0.70

évaluateur

-0.67

 мәкал

-0.65

ReusableCell

-0.58

errHandler

-0.57

 चीज़ों

-0.55

elemField

-0.53

 ✭✭

-0.52

HasIndex

-0.52

POSITIVE LOGITS

 препратки

0.40

 informations

0.40

 measurements

0.39

 measurement

0.39

 descrizione

0.38

 viktigt

0.38

 exigences

0.38

 belangrijk

0.37

 dedans

0.37

各项

0.37

Activations Density 0.023%

references to specific characteristics and specifications, particularly in a scientific or technical context

No Comments

No Known Activations