INDEX

Explanations

references to learning from experiences and mistakes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

lapsing

-0.50

roid

-0.45

odzi

-0.42

pot

-0.42

pod

-0.42

 Voit

-0.42

tari

-0.41

randint

-0.41

 Strickland

-0.41

makedirs

-0.40

POSITIVE LOGITS

 lessons

1.08

 leçons

1.07

 learnings

1.07

Lessons

1.04

 Lessons

1.01

lessons

0.97

 erfaring

0.94

 leçon

0.94

 Erfahrungen

0.90

 '\\;'

0.89

Activations Density 0.218%

references to learning from experiences and mistakes

No Comments

No Known Activations