INDEX

Explanations

numerical values related to quantities or monetary amounts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

findpost

-0.69

oredCriteria

-0.61

RectangleBorder

-0.59

 humeur

-0.56

 nonatomic

-0.56

 Chwiliwch

-0.55

存于互联网档案馆

-0.55

CodeAnalysis

-0.54

SPJ

-0.54

shops

-0.52

POSITIVE LOGITS

 dollars

1.39

 dollar

1.17

 Dollars

0.92

 Dollar

0.91

 pounds

0.86

 DOLLARS

0.86

dollar

0.85

 naira

0.84

naire

0.80

AIRE

0.80

Activations Density 0.140%

numerical values related to quantities or monetary amounts

No Comments

No Known Activations