INDEX

Explanations

specific names and their associations within 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 @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

èses

-0.49

-0.48

@[+][

-0.45

に至

-0.44

 alış

-0.42

↵

-0.42

-0.41

razos

-0.40

</h5>

-0.40

POSITIVE LOGITS

 autorytatywna

0.82

rungsseite

0.78

 Normdatei

0.76

 فريبيس

0.66

WebElementEntity

0.66

 MERCHANTABILITY

0.65

 архивлан

0.65

ViewImports

0.64

itespace

0.63

Ĝ

0.63

Activations Density 0.659%

specific names and their associations within various contexts

No Comments

No Known Activations