INDEX

Explanations

elements associated with legal or procedural discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

Datuak

-0.63

TestingModule

-0.61

tvguidetime

-0.59

 jScrollPane

-0.59

 disambiguazione

-0.57

DataAnnotations

-0.57

Hentet

-0.56

曖昧さ回避

-0.56

databind

-0.51

mkdirs

-0.50

POSITIVE LOGITS

 here

2.57

 allí

2.32

 dort

2.24

 там

2.19

 Allí

2.18

在那里

2.17

 acolo

1.96

 therein

1.89

 there

1.89

 آنجا

1.86

Activations Density 0.780%

elements associated with legal or procedural discussions

No Comments

No Known Activations