INDEX

Explanations

terms and phrases related to scientific and technical analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.35.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

#+#

-0.44

超

-0.36

esz

-0.35

 Alternate

-0.35

 super

-0.33

adaptiveStyles

-0.33

Alternate

-0.32

gång

-0.32

 самоу

-0.31

 ги

-0.31

POSITIVE LOGITS

 regular

0.85

 mainline

0.77

regular

0.76

 conventional

0.74

 mainstream

0.73

 mainland

0.73

 regulares

0.70

 general

0.68

 REGULAR

0.68

 Regular

0.67

Activations Density 2.238%

terms and phrases related to scientific and technical analysis

No Comments

No Known Activations