INDEX

Explanations

references to government or regulatory agencies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

-0.81

 Mould

-0.72

intre

-0.70

toPromise

-0.68

/**

-0.66

UInt

-0.66

PreExecute

-0.65

 CURLOPT

-0.65

 Meli

-0.64

 Steuer

-0.64

POSITIVE LOGITS

 Agencies

1.48

 agencies

1.47

Agencies

1.38

 Agency

1.34

agencies

1.32

 AGENCY

1.31

Agency

1.24

 agency

1.22

agency

1.21

 agencia

1.11

Activations Density 0.104%

references to government or regulatory agencies

No Comments

No Known Activations