INDEX

Explanations

programming constructs and their structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 itſelf

-0.67

 fhort

-0.60

 Jefus

-0.56

 myſelf

-0.56

хьтан

-0.56

aarrggbb

-0.55

 depositphotos

-0.55

źni

-0.53

$")

-0.53

"*.

-0.53

POSITIVE LOGITS

 chi̍t

0.62

новниш

0.54

 Lipp

0.53

 autorytatywna

0.53

AxisAlignment

0.52

 forKey

0.50

 consulter

0.50

imod

0.49

 vivement

0.48

éndole

0.48

Activations Density 0.024%

programming constructs and their structure

No Comments

No Known Activations