INDEX

Explanations

references to Donald Trump and his actions or statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 خارجية

-0.82

 Peoria

-0.74

 Ebert

-0.73

'{@

-0.72

 Stodd

-0.69

 Kearns

-0.69

Gli

-0.68

 itinerary

-0.68

_{*}

-0.68

 COLLE

-0.68

POSITIVE LOGITS

 Trump

1.75

Trump

1.52

trump

1.12

 trump

1.07

 Truman

0.95

特朗普

0.95

 Trumb

0.94

 trumpet

0.88

Donald

0.87

 trumpets

0.84

Activations Density 0.089%

references to Donald Trump and his actions or statements

No Comments

No Known Activations