INDEX

Explanations

numbers and numerical expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 للمعارف

-0.62

 liệt

-0.58

Välislingid

-0.56

pere

-0.55

 Azevedo

-0.55

 Gual

-0.54

 зая

-0.54

proz

-0.54

 drift

-0.53

ècie

-0.53

POSITIVE LOGITS

AndEndTag

0.82

رشف

0.74

 MainAxisSize

0.72

featureID

0.72

IntoConstraints

0.70

Amicalement

0.67

 يتيمه

0.65

abetes

0.64

AddTagHelper

0.63

 ModelExpression

0.63

Activations Density 1.443%

numbers and numerical expressions

No Comments

No Known Activations