INDEX

Explanations

specifications related to dimensions and layouts in a programming or graphical context

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

="#"><

-0.61

 Zusammen

-0.55

 ",";

-0.53

 Kirke

-0.52

 Ingo

-0.52

 atom

-0.51

chum

-0.50

 menti

-0.49

енча

-0.49

ǃ

-0.49

POSITIVE LOGITS

Height

1.93

HEIGHT

1.70

Width

1.63

 HEIGHT

1.34

 Height

1.31

 Width

1.20

WIDTH

1.13

SequentialGroup

1.10

height

1.08

getHeight

1.08

Activations Density 0.117%

specifications related to dimensions and layouts in a programming or graphical context

No Comments

No Known Activations