INDEX

Explanations

terms related to guidance or instructions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

forbes

-0.73

Morrison

-0.71

texttt

-0.71

 Kras

-0.70

},{

-0.68

 Ellington

-0.67

elsey

-0.66

beforeEach

-0.65

 Vill

-0.65

ServerError

-0.65

POSITIVE LOGITS

 guides

1.76

 guide

1.73

guide

1.67

Guides

1.67

 Guides

1.66

 Guide

1.62

Guide

1.60

 GUIDE

1.55

 guid

1.55

guides

1.54

Activations Density 0.095%

terms related to guidance or instructions

No Comments

No Known Activations