INDEX

Explanations

details about measurements and specifications in a technical or scientific context

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

Personendaten

-0.60

 kasarigan

-0.58

 gynhyrchwyd

-0.56

rungsseite

-0.55

Datuak

-0.54

 CURIAM

-0.49

 esternos

-0.48

 שוליים

-0.45

ReusableCell

-0.45

(!__

-0.45

POSITIVE LOGITS

Needs

0.47

needs

0.46

 require

0.46

 Needs

0.45

 needs

0.45

 requires

0.43

setLayoutManager

0.42

require

0.42

need

0.40

 requiring

0.40

Activations Density 0.883%

details about measurements and specifications in a technical or scientific context

No Comments

No Known Activations