INDEX

Explanations

acronyms and variables often used in scientific papers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

أ

-0.56

").

-0.55

Indented

-0.55

ensch

-0.54

].(

-0.53

ldr

-0.52

</s>

-0.51

mtd

-0.51

 grun

-0.51

 rene

-0.50

POSITIVE LOGITS

VIAF

1.41

 VIAF

1.18

fv

1.16

 Vance

1.15

getV

1.15

bv

1.14

DV

1.10

VH

1.09

 Voss

1.07

WV

1.06

Activations Density 2.522%

acronyms and variables often used in scientific papers

No Comments

No Known Activations