INDEX

Explanations

references to steps in a procedural or instructional context

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

marshaller

-0.48

has

-0.42

+#+

-0.41

Abp

-0.40

 auto

-0.40

FileSystem

-0.40

Naissance

-0.39

har

-0.39

mic

-0.38

 земля

-0.38

POSITIVE LOGITS

 ſind

0.82

EndInit

0.77

IntoConstraints

0.75

PreExecute

0.73

setVerticalGroup

0.72

fromnode

0.72

󠁴

0.72

webElement

0.70

 beginnetje

0.70

__":

0.70

Activations Density 0.223%

references to steps in a procedural or instructional context

No Comments

No Known Activations