INDEX

Explanations

log statements and logging related activities

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

 magát

-0.49

OrCreate

-0.43

ResumeLayout

-0.42

 ragioni

-0.42

 leeftijd

-0.40

 pohled

-0.40

bä

-0.40

قامة

-0.40

ISupport

-0.40

 mouvements

-0.39

POSITIVE LOGITS

info

1.27

 info

1.24

 Info

1.13

 INFO

1.08

INFO

1.04

Info

1.01

 warn

0.93

 informational

0.93

 information

0.89

 warning

0.88

Activations Density 0.207%

log statements and logging related activities

No Comments

No Known Activations