INDEX

Explanations

coded structures and programming syntax

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

`MANTIS` followed by another word

np_acts-logits-general · gemini-2.0-flash

MANTIS

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 Holbrook

-0.71

 Kirkpatrick

-0.67

 Schuyler

-0.66

 Clinton

-0.58

 kath

-0.58

 microm

-0.58

 Tompkins

-0.58

Koz

-0.58

Rab

-0.57

Rae

-0.56

POSITIVE LOGITS

MAN

1.47

 Manning

1.42

 Manny

1.38

 Mandel

1.28

 Mani

1.27

Manny

1.25

 Manchester

1.25

MAN

1.23

 Manley

1.22

 Mandy

1.18

Activations Density 0.516%

coded structures and programming syntax

`MANTIS` followed by another word

MANTIS

No Comments

No Known Activations

coded structures and programming syntax

`MANTIS` followed by another word

MANTIS

No Comments

No Known Activations