INDEX

Explanations

technical terms and parameters related to electronics and telecommunications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

ourne

-0.55

 Treat

-0.55

 khuôn

-0.54

 treatment

-0.53

참고

-0.53

 lenker

-0.52

ceny

-0.52

 secu

-0.51

 treated

-0.51

 Treatment

-0.51

POSITIVE LOGITS

WireFormat

0.60

enumii

0.59

JNIEnv

0.57

UseVisualStyle

0.56

writeField

0.54

tagext

0.52

dafx

0.50

upyter

0.50

 vaisselle

0.50

createClass

0.50

Activations Density 0.316%

technical terms and parameters related to electronics and telecommunications

No Comments

No Known Activations