INDEX

Explanations

technical terms related to data processing and analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

UrlResolution

-0.57

rawDesc

-0.54

WebElementEntity

-0.54

httphttps

-0.51

 Lightboxes

-0.49

EDEFAULT

-0.47

meiras

-0.46

存于互联网档案馆

-0.45

 autorytatywna

-0.44

ParallelGroup

-0.42

POSITIVE LOGITS

 horas

0.36

 Scholars

0.36

inWeight

0.35

 Students

0.35

 Mulher

0.34

 '\\;'

0.34

Follower

0.34

bootstrapcdn

0.34

cmath

0.33

Bride

0.33

Activations Density 0.433%

technical terms related to data processing and analysis

No Comments

No Known Activations