INDEX

Explanations

function definitions and their signatures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/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.9.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

ed

-0.76

-0.68

em

-0.67

Zat

-0.66

 Steen

-0.66

Zij

-0.66

Zit

-0.65

 kili

-0.64

 Harrow

-0.64

less

-0.63

POSITIVE LOGITS

func

1.61

 func

1.42

 Func

1.05

Func

0.96

Funcs

0.84

 nahilalakip

0.83

FUNC

0.83

ConstraintMaker

0.76

 الرياضيه

0.76

 للمعارف

0.76

Activations Density 0.053%

function definitions and their signatures

No Comments

No Known Activations