INDEX

Explanations

terms related to the development and improvement of mechanisms or products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

########.

-0.67

 otomatig

-0.63

Życiorys

-0.62

 NSCoder

-0.59

 TextAlign

-0.56

ChildScrollView

-0.55

 propOrder

-0.54

nonatomic

-0.50

igshid

-0.50

uxxxx

-0.49

POSITIVE LOGITS

 designing

0.81

develop

0.78

 concevoir

0.78

 develop

0.75

 innovate

0.74

]));

0.73

Designing

0.73

 researching

0.72

 innovations

0.71

 разрабо

0.70

Activations Density 0.668%

terms related to the development and improvement of mechanisms or products

No Comments

No Known Activations