INDEX

Explanations

numerical data or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

TypedDataSet

-0.72

 nahilalakip

-0.68

complexContent

-0.65

wieś

-0.58

★★★★☆

-0.57

 Sakit

-0.56

 nawr

-0.53

 nonatomic

-0.52

irut

-0.52

ⓧ

-0.52

POSITIVE LOGITS

 kasarigan

0.84

AddTagHelper

0.69

PreferredItem

0.54

IVEREF

0.53

Lycka

0.52

twimg

0.51

ötz

0.51

 Sioux

0.50

{?>

0.50

uerta

0.49

Activations Density 1.377%

numerical data or statistics

No Comments

No Known Activations