INDEX

Explanations

parameter tags typically found in technical specifications or code configurations

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

 écou

-0.65

 CURLOPT

-0.64

 noqa

-0.64

(()=>{

-0.62

EMBL

-0.62

 tenuta

-0.60

{|

-0.59

IEU

-0.59

venu

-0.59

ungk

-0.59

POSITIVE LOGITS

 commissioners

0.70

SpringRunner

0.66

 विश्वसनीयता

0.65

param

0.64

 hydrochloride

0.58

+#+#

0.58

Zav

0.56

 param

0.55

Chú

0.55

 Theorem

0.54

Activations Density 0.146%

parameter tags typically found in technical specifications or code configurations

No Comments

No Known Activations