INDEX

Explanations

patterns in regular expressions used for matching specific data formats or structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.51

–

-0.45

-0.42

 respect

-0.41

<eos>

-0.41

Respectfully

-0.40

-0.39

POSITIVE LOGITS

rungsseite

0.91

出版年

0.85

 الحره

0.85

 surla

0.82

IntoConstraints

0.81

 disambiguazione

0.78

脚注の使い方

0.77

InputBorder

0.76

([

0.75

Xna

0.74

Activations Density 0.220%

patterns in regular expressions used for matching specific data formats or structures

No Comments

No Known Activations