INDEX

Explanations

references to processes and steps involved in measured activities or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

%)$

-0.57

 jouets

-0.52

 élections

-0.49

存于互联网档案馆

-0.49

 vœux

-0.49

 enseignants

-0.48

ylabel

-0.48

Portale

-0.48

 maternelle

-0.48

 pouvoirs

-0.47

POSITIVE LOGITS

 chunks

1.39

 bursts

1.31

 intervals

1.29

 segments

1.24

 fragments

1.19

 bits

1.17

 snippets

1.16

 increments

1.16

 intermittent

1.12

chunks

1.09

Activations Density 0.496%

references to processes and steps involved in measured activities or actions

No Comments

No Known Activations