INDEX

Explanations

numeric values related to measurements and weights

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

렷

-0.54

 buckets

-0.54

verifyException

-0.53

ousands

-0.53

 bucket

-0.53

 Bucket

-0.52

 resourceCulture

-0.52

manteau

-0.51

 کیلو

-0.50

 HasFactory

-0.50

POSITIVE LOGITS

oz

0.79

oz

0.76

 ounces

0.76

 grams

0.73

 gram

0.73

gram

0.71

 ounce

0.71

grams

0.68

OZ

0.66

 Gram

0.60

Activations Density 0.234%

numeric values related to measurements and weights

No Comments

No Known Activations