INDEX

Explanations

references to diseases and health-related topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

PhysRev

-0.57

Asimismo

-0.54

 aforesaid

-0.52

 getItemId

-0.51

 deepcopy

-0.51

principalColumn

-0.51

memberof

-0.50

 hereinafter

-0.49

 valamint

-0.48

 MediatR

-0.47

POSITIVE LOGITS

Why

1.02

why

1.00

 Example

0.95

Why

0.95

why

0.94

Example

0.93

WHY

0.92

 example

0.85

example

0.84

How

0.84

Activations Density 0.068%

references to diseases and health-related topics

No Comments

No Known Activations