INDEX

Explanations

terms related to datasets and their attributes in a machine learning context

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

Mathematical or algorithmic terms

np_acts-logits-general · gemini-2.0-flash

neural network regularization and parameters

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 hefyd

-0.45

indrome

-0.43

 retort

-0.43

 marks

-0.43

 indented

-0.43

 remand

-0.42

 Corn

-0.41

арак

-0.41

 fetched

-0.41

ortable

-0.41

POSITIVE LOGITS

 regularization

0.67

 negative

0.66

 weight

0.66

Билгалдахарш

0.65

 weighting

0.64

 weights

0.63

weight

0.62

AsUp

0.62

 penalty

0.62

negative

0.61

Activations Density 0.690%

terms related to datasets and their attributes in a machine learning context

Mathematical or algorithmic terms

neural network regularization and parameters

No Comments

No Known Activations