INDEX

Explanations

references to "structure" in relation to various contexts

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

 repens

-1.13

 veneta

-1.07

 isoto

-0.92

 comets

-0.89

 Obsidian

-0.87

WebVitals

-0.86

 Noct

-0.86

 Yuma

-0.85

 Tenta

-0.85

 piety

-0.85

POSITIVE LOGITS

 structure

1.53

 structures

1.34

 Structure

1.19

structure

1.18

Structure

1.10

 STRUCTURE

1.09

structures

1.06

truct

1.03

 Structures

1.00

 Stru

0.97

Activations Density 0.081%

references to "structure" in relation to various contexts

No Comments

No Known Activations