INDEX

Explanations

technical terms and code structures related to programming and software design

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 Púb

-0.47

 friv

-0.47

}`).

-0.42

çoit

-0.41

Unsere

-0.41

rohr

-0.40

Джерела

-0.40

="?

-0.39

 Ranges

-0.39

POSITIVE LOGITS

IndentedString

0.90

ConstraintMaker

0.86

DockStyle

0.86

WebpackPlugin

0.76

 GenerationType

0.76

OrEqual

0.72

انيف

0.72

hdashline

0.70

SourceChecksum

0.69

OrNil

0.68

Activations Density 2.516%

technical terms and code structures related to programming and software design

No Comments

No Known Activations