INDEX

Explanations

concepts related to problem-solving and feature selection in the context of machine learning and data analysis

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

alloy

-0.47

 Polsce

-0.45

حياته

-0.43

 arrêté

-0.43

ordning

-0.42

 allele

-0.41

 dobrze

-0.41

Gemeinde

-0.41

することができます

-0.41

 covenant

-0.41

POSITIVE LOGITS

fjspx

0.78

ISupport

0.74

NameInMap

0.73

SBATCH

0.69

новниш

0.64

']));

0.58

"]));

0.58

रीदारी

0.57

AddHtmlAttribute

0.57

])):

0.57

Activations Density 0.950%

concepts related to problem-solving and feature selection in the context of machine learning and data analysis

No Comments

No Known Activations