INDEX

Explanations

references to Donald Trump and his actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

tagHelperRunner

-0.81

vara

-0.75

jasama

-0.66

Ber

-0.65

 disambiguazione

-0.63

 Ebert

-0.62

 Xing

-0.62

Tea

-0.62

={({

-0.61

 LoggerFactory

-0.61

POSITIVE LOGITS

 Trump

1.91

Trump

1.76

trump

1.43

 trump

1.32

特朗普

1.03

Donald

0.98

 Donald

0.95

 DONALD

0.87

 trumpet

0.84

 donald

0.84

Activations Density 0.103%

references to Donald Trump and his actions

No Comments

No Known Activations