INDEX

Explanations

references to secrecy and activities occurring out of public view

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

CppMethod

-0.63

PMailer

-0.53

virons

-0.52

 Infórmanos

-0.50

UnsafeEnabled

-0.48

 omge

-0.47

WAUKEE

-0.47

 noqa

-0.47

MigrationBuilder

-0.44

oges

-0.43

POSITIVE LOGITS

 scenes

1.26

 Behind

1.17

 behind

1.13

Behind

1.13

 BEHIND

1.10

scenes

1.09

behind

1.07

 Scenes

0.99

Scenes

0.99

 closed

0.90

Activations Density 0.059%

references to secrecy and activities occurring out of public view

No Comments

No Known Activations