INDEX

Explanations

terms related to feature selection and optimization in data analysis contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

ImageField

-0.60

-0.53

egg

-0.52

Ab

-0.52

+#+#

-0.52

van

-0.51

Ay

-0.49

 تانيه

-0.48

 last

-0.48

 imageNamed

-0.46

POSITIVE LOGITS

 Diſ

0.86

TargetException

0.84

 itſelf

0.81

 ſche

0.78

 becauſe

0.76

 myſelf

0.75

 ſever

0.75

 uſed

0.74

 Monfieur

0.74

 Theſe

0.73

Activations Density 1.248%

terms related to feature selection and optimization in data analysis contexts

No Comments

No Known Activations