INDEX

Explanations

references to political figures and scandals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

IRR

-0.31

 raccomand

-0.29

 lädt

-0.28

 prospect

-0.27

 visiter

-0.27

 instructed

-0.27

 instructs

-0.27

 instructions

-0.27

 toege

-0.27

PositiveButton

-0.27

POSITIVE LOGITS

 EconPapers

0.77

principalTable

0.76

 ویکی‌پدی

0.72

SharedCtor

0.71

 revelations

0.69

BeginContext

0.69

 صوتيه

0.68

 surla

0.65

 disclosure

0.65

DockStyle

0.65

Activations Density 0.592%

references to political figures and scandals

No Comments

No Known Activations