INDEX

Explanations

references to key figures and organizations in governance or politics

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

NUMX

-1.03

 ་་

-1.01

 Majefty

-1.00

 myſelf

-0.95

 XNUMX

-0.93

 itſelf

-0.90

Yah

-0.88

 ſeveral

-0.88

 Anſ

-0.86

 Hift

-0.85

POSITIVE LOGITS

 till

0.64

 upto

0.64

 organised

0.64

NoOf

0.61

noOf

0.60

upto

0.57

 acompañado

0.57

0.56

<eos>

0.55

 samme

0.54

Activations Density 1.397%

references to key figures and organizations in governance or politics

No Comments

No Known Activations