INDEX

Explanations

questions and inquiries regarding definitions and processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

تقاوى

-0.64

resave

-0.61

脚注の使い方

-0.61

Kaieteur

-0.59

AutoScaleMode

-0.56

wek

-0.55

Хьажоргаш

-0.54

 INSEE

-0.54

">=

-0.53

ero

-0.52

POSITIVE LOGITS

 myſelf

0.72

Why

0.69

What

0.69

 Diſ

0.67

0.66

QtWidgets

0.62

How

0.60

 juſ

0.59

 ſta

0.58

 purpoſe

0.58

Activations Density 0.240%

questions and inquiries regarding definitions and processes

No Comments

No Known Activations