INDEX

Explanations

concepts related to elevation, raising, and improvement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

uttgart

-0.71

 "..\..\..\

-0.65

ETHING

-0.62

rawDesc

-0.55

atimes

-0.55

rager

-0.54

 "..\..\

-0.53

mphony

-0.51

 XCTest

-0.50

 Dernière

-0.50

POSITIVE LOGITS

 higher

1.28

 high

1.27

 heights

1.27

 elevation

1.24

 tinggi

1.24

 Higher

1.22

 elevated

1.22

 raised

1.21

Higher

1.20

HIGH

1.19

Activations Density 0.674%

concepts related to elevation, raising, and improvement

No Comments

No Known Activations

concepts related to elevation, raising, and improvement

No Comments

No Known Activations