INDEX

Explanations

references to quantities or counts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Abitanti

-0.61

NOPQRST

-0.58

__;

-0.56

Ờ

-0.54

reuung

-0.53

giène

-0.52

lossene

-0.51

 للاسماء

-0.51

 تضيفلها

-0.50

 ✭✭

-0.50

POSITIVE LOGITS

 months

2.34

 weeks

2.31

 years

2.26

 days

1.94

 month

1.84

months

1.80

years

1.78

 Months

1.76

weeks

1.75

 week

1.69

Activations Density 0.353%

references to quantities or counts

No Comments

No Known Activations