INDEX

Explanations

keywords or terminology related to data management and manipulation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

出版年

-0.69

 Lando

-0.67

SharedCtor

-0.66

]){

-0.65

ropho

-0.65

 ―――――

-0.64

==""){

-0.62

CWE

-0.60

ney

-0.60

AutoresizingMask

-0.60

POSITIVE LOGITS

 this

0.90

 these

0.88

 them

0.65

 questo

0.62

 queste

0.61

these

0.59

 diesen

0.58

 этих

0.57

 questa

0.56

 этот

0.56

Activations Density 0.593%

keywords or terminology related to data management and manipulation

No Comments

No Known Activations