INDEX

Explanations

notes or references in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 DriverManager

-0.76

 Brito

-0.64

imum

-0.61

 BoxFit

-0.61

ிரு

-0.61

ALITY

-0.61

libur

-0.60

Perché

-0.59

getSystemService

-0.59

initializeApp

-0.59

POSITIVE LOGITS

 notes

1.42

 Notes

1.39

 note

1.37

 NOTE

1.32

 Note

1.27

notes

1.23

 NOTES

1.20

Notes

1.20

noted

1.17

note

1.15

Activations Density 0.066%

notes or references in the text

No Comments

No Known Activations