INDEX

Explanations

references to diagrams and data related to scientific findings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

+#+#

-0.90

 Crud

-0.79

ReusableCell

-0.75

 Manta

-0.74

CreateModel

-0.74

 Krak

-0.73

 препратки

-0.71

 previa

-0.70

eah

-0.70

éfono

-0.70

POSITIVE LOGITS

Di

1.23

 Dietz

1.19

di

1.18

Di

1.14

 DiCaprio

1.14

DI

1.09

di

1.03

DI

1.01

 Dial

0.99

 Diab

0.97

Activations Density 0.226%

references to diagrams and data related to scientific findings

No Comments

No Known Activations