INDEX

Explanations

keywords and phrases related to academic and professional achievements or recognition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

JAXB

-0.52

TintMode

-0.46

liyor

-0.44

circledR

-0.44

indeki

-0.43

 насељу

-0.43

TypedDataSet

-0.43

########.

-0.43

MathML

-0.42

}}-

-0.41

POSITIVE LOGITS

 fieldNum

0.74

IntoConstraints

0.72

存于互联网档案馆

0.68

 ModelExpression

0.67

InSection

0.66

featureID

0.61

Vanjske

0.60

 item

0.58

 EClass

0.58

yoshi

0.58

Activations Density 0.948%

keywords and phrases related to academic and professional achievements or recognition

No Comments

No Known Activations