INDEX

Explanations

names and titles associated with research or academic work

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

جمعیت

-0.51

Coordenadas

-0.48

 prati

-0.47

 vẽ

-0.46

 difference

-0.44

zędu

-0.44

exif

-0.43

onomia

-0.43

 again

-0.42

 Antibodies

-0.42

POSITIVE LOGITS

ts

1.20

AndEndTag

0.88

 autorytatywna

0.79

TS

0.78

__":

0.75

")){

0.74

}")

0.72

 fieldNum

0.70

ets

0.69

tsin

0.69

Activations Density 2.102%

names and titles associated with research or academic work

No Comments

No Known Activations