INDEX

Explanations

terminology related to choices and selections

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

leswig

-0.70

 مرئيه

-0.69

 pitié

-0.68

 وتسجيلات

-0.66

клопе

-0.65

 pinulongan

-0.62

 saurait

-0.62

AllowUser

-0.62

%");

-0.61

 eccl

-0.61

POSITIVE LOGITS

 choice

3.54

 Choice

3.29

choice

3.27

Choice

3.12

 CHOICE

3.06

 choices

2.66

CHOICE

2.64

 Choices

2.36

 choix

2.31

choices

2.23

Activations Density 0.080%

terminology related to choices and selections

No Comments

No Known Activations