INDEX

Explanations

terms related to warranty and liability in software documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 betweenstory

-0.79

titleMargin

-0.77

FormTagHelper

-0.76

 تز

-0.61

 ویکی‌پدی

-0.59

 kasarigan

-0.58

 kaarangay

-0.58

 Мексичка

-0.58

 nonUne

-0.57

Spoljašnje

-0.57

POSITIVE LOGITS

PREFERRED

4.37

 Preferred

1.59

 preferred

1.58

Preferred

1.54

preferred

1.48

REFERRED

1.07

 prefer

0.92

setPreferred

0.92

 preferable

0.90

 оригіналу

0.89

Activations Density 0.008%

terms related to warranty and liability in software documentation

No Comments

No Known Activations