INDEX

Explanations

references to expected values or expectations in statistical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 insuffisamment

-0.79

kring

-0.68

etheless

-0.67

POSIT

-0.64

ONAUT

-0.63

 Athen

-0.63

 ***!

-0.63

 Hitch

-0.62

 PropertyChanged

-0.62

 externi

-0.62

POSITIVE LOGITS

2.70

2.58

getE

1.64

Ｅ

1.31

cE

1.25

Е

1.19

xE

1.18

dE

1.16

Э

1.16

dE

1.14

Activations Density 0.100%

references to expected values or expectations in statistical contexts

No Comments

No Known Activations