INDEX

Explanations

references to personal experiences and skills

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

Laughs

-0.51

buttonBar

-0.49

ClientRect

-0.48

licone

-0.48

TouchListener

-0.47

俑

-0.46

μως

-0.46

มาย

-0.46

opedia

-0.46

tively

-0.46

POSITIVE LOGITS

 springfox

0.67

 Мексичка

0.61

adaptiveStyles

0.60

tagext

0.58

 AssemblyTitle

0.58

getMenuInflater

0.57

AsUp

0.56

 doInBackground

0.56

COUVER

0.56

revenge

0.54

Activations Density 0.397%

references to personal experiences and skills

No Comments

No Known Activations