INDEX

Explanations

speeches and quotes attributed to individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/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.19.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

Cordialement

-0.67

Jîn

-0.64

 tumors

-0.64

 himſelf

-0.61

تفصیلات

-0.61

 purpoſe

-0.60

 itſelf

-0.59

 harbors

-0.58

 poffible

-0.58

nyataan

-0.58

POSITIVE LOGITS

 snippetHide

0.57

 berkata

0.51

0.50

 programme

0.48

ंदीखरीदारी

0.46

):

0.45

Mr

0.44

CloseOperation

0.43

(*)

0.42

programme

0.41

Activations Density 0.038%

speeches and quotes attributed to individuals

No Comments

No Known Activations