INDEX

Explanations

quantitative measurements or references to large quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

@"/

-0.79

 ['./

-0.63

 wireType

-0.62

ioc

-0.59

ɵɵ

-0.58

 Smyth

-0.57

ObjectContext

-0.57

<em>

-0.57

complexContent

-0.56

どうか

-0.55

POSITIVE LOGITS

 thousands

1.31

 hundreds

1.23

thousands

1.20

 millions

1.15

 billions

1.14

 Thousands

1.13

 Hundreds

1.12

Hundreds

1.12

Thousands

1.12

hundreds

1.10

Activations Density 0.109%

quantitative measurements or references to large quantities

No Comments

No Known Activations