INDEX

Explanations

terms related to vertical and horizontal orientations or alignments

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

AsUp

-0.95

 Roskov

-0.86

oredCriteria

-0.82

+#+#

-0.79

fjspx

-0.74

 Signalez

-0.73

 Normdatei

-0.72

numerusform

-0.70

AutoField

-0.69

TestingModule

-0.68

POSITIVE LOGITS

 orientation

0.61

 Horizontal

0.56

方向

0.54

 axis

0.54

yaxis

0.52

 movement

0.52

 horizontal

0.52

 Vertical

0.51

 BorderSide

0.51

 asympto

0.51

Activations Density 0.188%

terms related to vertical and horizontal orientations or alignments

No Comments

No Known Activations