INDEX

Explanations

negative descriptions and sentiments related to experiences or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 VIAF

-0.77

stateProvider

-0.77

VIAF

-0.76

 AspNetCore

-0.75

createCanvas

-0.75

 Baillargeon

-0.73

 AssemblyCompany

-0.73

providedIn

-0.71

balleur

-0.67

POSITIVE LOGITS

 worst

1.31

 horrible

1.27

Worse

1.24

 worse

1.22

 terrible

1.21

 Worst

1.18

worst

1.16

worse

1.12

Worst

1.11

 Worse

1.10

Activations Density 0.184%

negative descriptions and sentiments related to experiences or concepts

No Comments

No Known Activations