INDEX

Explanations

numerical values or significant figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

leč

-0.52

con

-0.52

ez

-0.51

낙

-0.51

&$

-0.50

více

-0.50

mas

-0.49

획

-0.49

fillText

-0.48

 tissue

-0.47

POSITIVE LOGITS

 للاسماء

0.98

httphttps

0.80

 }}"></

0.80

intios

0.75

0.71

BeginContext

0.69

":[{

0.68

__":

0.67

 smtplib

0.66

₁,

0.66

Activations Density 0.011%

numerical values or significant figures

No Comments

No Known Activations