INDEX

Explanations

references to Microsoft and its products

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

脚注の使い方

-0.62

новниш

-0.59

stopp

-0.58

atern

-0.55

mora

-0.55

tros

-0.55

andowski

-0.54

iony

-0.54

 stret

-0.54

parametrize

-0.53

POSITIVE LOGITS

MS

3.23

MS

3.15

ms

2.99

ms

2.98

Ms

1.97

Ms

1.96

MSD

1.66

MSF

1.41

MSD

1.41

msa

1.29

Activations Density 0.065%

references to Microsoft and its products

No Comments

No Known Activations