INDEX

Explanations

phrases that indicate classification or categorization

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 braccia

-0.67

 unut

-0.63

 cauſe

-0.62

 quæ

-0.61

 vertes

-0.61

 pleaſure

-0.58

 purpoſe

-0.58

 poitrine

-0.57

 exceptionnelle

-0.56

 fubject

-0.56

POSITIVE LOGITS

Kinda

1.15

 sorta

1.07

complexContent

1.05

 Kinda

1.03

EndInit

0.94

kinda

0.93

 kinda

0.91

 оригіналу

0.91

GroupLayout

0.88

Somewhat

0.86

Activations Density 0.103%

phrases that indicate classification or categorization

No Comments

No Known Activations