INDEX

Explanations

occurrences of the word "a" in various forms and contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 investi

-0.78

 enthusi

-0.76

 encom

-0.70

 expli

-0.69

 lemp

-0.69

 opis

-0.69

 vider

-0.68

 incor

-0.68

 compri

-0.68

 iſt

-0.67

POSITIVE LOGITS

1.28

1.26

getA

1.22

1.06

0.99

aA

0.88

aData

0.88

 ansatte

0.86

QApplication

0.81

bA

0.81

Activations Density 0.345%

occurrences of the word "a" in various forms and contexts

No Comments

No Known Activations