INDEX

Explanations

references to mathematical matrices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 oignons

-0.74

 Toul

-0.74

 scarpe

-0.74

Calla

-0.69

isSuccessful

-0.63

 taches

-0.62

 Gogh

-0.61

 giả

-0.61

ядок

-0.60

ibouti

-0.60

POSITIVE LOGITS

 nonatomic

1.08

PDS

1.06

 matrices

0.97

nonatomic

0.95

 Matrices

0.88

 Matrix

0.87

RenderAtEndOf

0.87

Bibliograf

0.85

NonQuery

0.84

arie

0.84

Activations Density 0.082%

references to mathematical matrices

No Comments

No Known Activations