INDEX

Explanations

references to historical or significant figures and events

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

 queſta

-0.59

+#+#

-0.58

 purpoſe

-0.55

 itſelf

-0.55

 foon

-0.54

clerView

-0.54

 fuzzy

-0.53

 myſelf

-0.53

 furry

-0.52

mpagne

-0.52

POSITIVE LOGITS

enumi

0.45

Véxase

0.40

aarrggbb

0.38

xsi

0.38

úgó

0.35

 Volkes

0.34

McM

0.32

 Chwiliwch

0.32

fjspx

0.31

LookAnd

0.31

Activations Density 0.099%

references to historical or significant figures and events

No Comments

No Known Activations