INDEX

Explanations

Java annotations and access modifiers within class definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 <=",

-0.56

-0.50

lib

-0.47

rg

-0.47

-0.45

-0.42

émoc

-0.41

nal

-0.41

 geblieben

-0.41

 Generale

-0.41

POSITIVE LOGITS

脚注の使い方

0.93

出版年

0.76

 sockaddr

0.76

 كومونز

0.75

✨:

0.74

GEBURTS

0.74

Lähteet

0.73

saraba

0.73

AddHtmlAttribute

0.73

 дописавши

0.73

Activations Density 0.043%

Java annotations and access modifiers within class definitions

No Comments

No Known Activations