INDEX

Explanations

terms related to scientific research and methodologies

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

IFrame

Link

Negative Logits

contentLoaded

-1.08

$_"

-0.91

UnusedPrivate

-0.89

 InputDecoration

-0.88

InjectAttribute

-0.86

 cherchés

-0.85

hdashline

-0.83

 Exactos

-0.83

帖最后由

-0.82

enumii

-0.81

POSITIVE LOGITS

SPATH

0.49

re

0.42

covo

0.40

executeUpdate

0.39

put

0.38

 attempted

0.37

bindValue

0.37

 perform

0.36

 commit

0.36

 vaccin

0.36

Activations Density 0.881%

terms related to scientific research and methodologies

No Known Activations