INDEX

Explanations

references to individuals of political significance or authority

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

 AssemblyCulture

-1.30

Manbalar

-1.25

存于互联网档案馆

-1.16

 Rasp

-1.16

thest

-1.12

makeConstraints

-1.12

 configureStore

-1.11

onAttach

-1.10

 prosegu

-1.09

Brainz

-1.08

POSITIVE LOGITS

1.72

1.55

1.28

1.26

1.25

1.23

ه

1.18

1.16

er

1.15

yny

1.11

Activations Density 4.858%

references to individuals of political significance or authority

No Comments

No Known Activations