INDEX

Explanations

comparisons and discussions related to past presidents, particularly in the context of political actions and their consequences

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

U.S. presidents

np_acts-logits-general · gemini-2.0-flash

president followed by names

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 שוליים

-0.59

 للمعارف

-0.57

XmlAccessType

-0.53

 getFile

-0.50

ức

-0.49

telser

-0.48

setupUi

-0.48

 Dietz

-0.48

 UIFont

-0.47

deth

-0.47

POSITIVE LOGITS

 Obama

1.69

 Trump

1.61

 Barack

1.59

 President

1.46

Trump

1.41

Obama

1.41

 Biden

1.35

 Donald

1.34

President

1.32

 Bush

1.20

Activations Density 0.436%

comparisons and discussions related to past presidents, particularly in the context of political actions and their consequences

U.S. presidents

president followed by names

No Known Activations