INDEX

Explanations

structures and formatting indicators within technical documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

is

-0.48

ázka

-0.45

 senti

-0.42

ville

-0.40

pal

-0.40

hit

-0.39

 показа

-0.36

POSITIVE LOGITS

 שוליים

1.01

}}$\\

0.88

+:+

0.78

&&

0.77

 pinulongan

0.77

ⓧ

0.75

IUrlHelper

0.74

MLLoader

0.74

StoryboardSegue

0.74

ValueStyle

0.73

Activations Density 0.377%

structures and formatting indicators within technical documents

No Comments

No Known Activations