INDEX

Explanations

references to software versions and related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 makeStyles

-0.73

delaire

-0.72

 InputDecoration

-0.72

avajillas

-0.70

utnik

-0.70

ulents

-0.70

HCC

-0.69

ungkinan

-0.69

makeConstraints

-0.69

/>";

-0.69

POSITIVE LOGITS

 VERSION

1.48

 Version

1.44

 version

1.41

 versions

1.41

Version

1.37

VERSION

1.32

version

1.31

 Versions

1.21

 getVersion

1.18

getVersion

1.15

Activations Density 0.123%

references to software versions and related terminology

No Comments

No Known Activations