INDEX

Explanations

references to tables and seating arrangements

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

量

-0.51

ⓘ

-0.50

withOpacity

-0.48

 condoms

-0.48

ppe

-0.48

 poudre

-0.48

 doInBackground

-0.47

 perte

-0.47

ত্ত

-0.47

hells

-0.47

POSITIVE LOGITS

 table

1.52

 tables

1.49

 desk

1.31

 tafel

1.25

 Tables

1.24

 desks

1.23

 tavolo

1.19

 Tisch

1.18

 TABLES

1.14

 meja

1.10

Activations Density 0.145%

references to tables and seating arrangements

No Comments

No Known Activations