INDEX

Explanations

references to Donald Trump and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

teto

-0.65

 Obre

-0.62

\{\\

-0.61

Filmografie

-0.60

漕

-0.59

довлет

-0.59

'{@

-0.59

wieś

-0.57

occasione

-0.57

 Leite

-0.56

POSITIVE LOGITS

 Trump

2.46

Trump

2.28

 trump

1.69

trump

1.64

 Donald

1.30

特朗普

1.26

Donald

1.25

 DONALD

1.19

 donald

1.09

 trumpet

1.03

Activations Density 0.055%

references to Donald Trump and related terms

No Comments

No Known Activations