INDEX

Explanations

textual elements indicating quoting or reporting of speech

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 nakalista

-0.50

contentLoaded

-0.42

 للاسماء

-0.40

 թվական

-0.39

Mirror

-0.37

 strips

-0.37

 beers

-0.37

 beira

-0.36

 destination

-0.36

 Mirror

-0.36

POSITIVE LOGITS

providedIn

0.52

 propOrder

0.49

 &___

0.48

SOUNDBITE

0.47

onViewCreated

0.46

 OnInit

0.46

RFI

0.45

 surla

0.45

insics

0.44

parsedMessage

0.43

Activations Density 0.075%

textual elements indicating quoting or reporting of speech

No Comments

No Known Activations