INDEX

Explanations

reference to byte data types and their representations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 myſelf

-1.43

 purpoſe

-1.34

ſelf

-1.32

 Jefus

-1.32

 itſelf

-1.30

Efq

-1.29

 pleaſure

-1.28

 themſelves

-1.26

 juſ

-1.25

 iſt

-1.23

POSITIVE LOGITS

byte

0.80

 bite

0.68

 byte

0.67

 bites

0.65

0.61

 bytes

0.60

bytes

0.60

jet

0.60

Activations Density 0.108%

reference to byte data types and their representations

No Comments

No Known Activations