INDEX

Explanations

references to numbers, specifically those that denote counts or parameters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 demais

-0.81

Tembelea

-0.80

 juſt

-0.79

 pObj

-0.79

 leaſt

-0.79

 tfsi

-0.78

 poffible

-0.78

"\<

-0.77

 flèche

-0.76

 Borja

-0.76

POSITIVE LOGITS

 number

1.79

 Number

1.68

 NUMBER

1.63

Number

1.60

 numbers

1.55

number

1.53

NUMBER

1.51

 Numbers

1.39

Numbers

1.34

numbers

1.32

Activations Density 0.084%

references to numbers, specifically those that denote counts or parameters

No Comments

No Known Activations