INDEX

Explanations

symbols and formatting related to programming and code structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 auroit

-0.77

 échanges

-0.77

 refroid

-0.75

 illustrazione

-0.73

 sécher

-0.73

 colgantes

-0.73

 nicio

-0.72

 calitate

-0.72

 aéri

-0.71

 scienza

-0.70

POSITIVE LOGITS

 mono

0.52

fos

0.49

前

0.48

 CHORUS

0.48

 manis

0.48

 flat

0.46

 Denis

0.46

Mono

0.45

 ters

0.45

mono

0.44

Activations Density 0.329%

symbols and formatting related to programming and code structure

No Comments

No Known Activations