INDEX

Explanations

references to specific mathematical or procedural formulas

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

 Kear

-0.61

KommentareTeilen

-0.60

 Pall

-0.59

lights

-0.59

Ligações

-0.58

setObjectName

-0.57

 Depp

-0.57

 KeyEvent

-0.57

extent

-0.57

Jol

-0.56

POSITIVE LOGITS

 formula

2.72

 formulas

2.61

 Formula

2.53

formula

2.51

Formula

2.50

 FORMULA

2.39

 formulae

2.35

 formule

2.24

 Formulas

2.24

 formules

2.06

Activations Density 0.105%

references to specific mathematical or procedural formulas

No Comments

No Known Activations