INDEX

Explanations

technical terms and concepts related to databases and data processing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

AddTagHelper

-1.00

contentLoaded

-0.81

NOPQRST

-0.78

 AssemblyCulture

-0.76

Manbalar

-0.72

хьтан

-0.72

AndEndTag

-0.70

 ویکی‌پدی

-0.70

TagMode

-0.69

 Meksiku

-0.69

POSITIVE LOGITS

 whichever

0.89

 whatever

0.82

any

0.76

 quelconque

0.76

 depending

0.72

 alguma

0.68

 quelcon

0.67

whatever

0.66

 alguno

0.64

 algum

0.63

Activations Density 0.407%

technical terms and concepts related to databases and data processing

No Comments

No Known Activations