INDEX

Explanations

references to achievements or accolades

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

ंदीखरीदारी

-0.77

 autorytatywna

-0.75

RegressionTest

-0.68

RTLU

-0.66

Vidite

-0.66

〮

-0.65

 nahilalakip

-0.65

adaptiveStyles

-0.64

 invokingState

-0.64

StoryboardSegue

-0.63

POSITIVE LOGITS

 earned

0.56

 Earned

0.35

earned

0.35

</u>

0.34

age

0.33

 suele

0.32

✭✭

0.32

 choice

0.32

 deserved

0.31

Age

0.30

Activations Density 0.029%

references to achievements or accolades

No Comments

No Known Activations