INDEX

Explanations

phrases indicating classification or characterization of concepts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bootstrapcdn

-1.03

 EconPapers

-1.01

 Majefty

-0.97

apimachinery

-0.93

DockStyle

-0.81

^(@)

-0.80

();)

-0.79

 referenties

-0.78

uestamente

-0.76

 Houſe

-0.76

POSITIVE LOGITS

 نظ

0.43

可以说

0.42

::

0.41

 Biro

0.40

ago

0.40

worthy

0.39

gement

0.39

ölkerung

0.39

arg

0.39

to

0.39

Activations Density 0.637%

phrases indicating classification or characterization of concepts

No Comments

No Known Activations