INDEX

Explanations

mathematical expressions and operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113

Prompts (Dashboard)

24,576 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

olar

-0.41

 '\\;'

-0.36

oa̍t

-0.35

Bioaccumulative

-0.35

፩

-0.35

 onData

-0.35

 interruptions

-0.34

Alguna

-0.34

Mayor

-0.33

 unproductive

-0.33

POSITIVE LOGITS

 <<<<<<<<<<<<<<

0.58

 ModelExpression

0.53

 disambiguazione

0.48

PreAuthorize

0.48

Parcelize

0.46

RRect

0.45

henswürdigkeiten

0.45

avigation

0.45

 Biôgrafia

0.44

iritto

0.44

Activations Density 1.679%

mathematical expressions and operations

No Comments

No Known Activations