INDEX

Explanations

terms related to precision and accuracy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 onOptions

-0.90

ciclop

-0.86

slidesPer

-0.84

 Montal

-0.77

 Sard

-0.71

 فريبيس

-0.70

 Eins

-0.70

xase

-0.70

 المعيارى

-0.70

Портал

-0.70

POSITIVE LOGITS

theless

0.93

 doughnuts

0.89

webElementXpaths

0.84

jména

0.81

tably

0.81

='';

0.80

,’

0.80

 Erdoğan

0.79

skine

0.79

 RIPRODUZIONE

0.78

Activations Density 0.213%

terms related to precision and accuracy

No Comments

No Known Activations