INDEX

Explanations

references to specific individuals and events in political contexts

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tanleria

-0.70

StoryboardSegue

-0.64

Tembelea

-0.63

onViewCreated

-0.62

Carriera

-0.62

KEYCODE

-0.58

Bước

-0.57

ArgumentParser

-0.56

enggarakan

-0.56

Hentet

-0.55

POSITIVE LOGITS

 Trump

1.32

Trump

1.19

 Donald

0.89

Donald

0.84

trump

0.76

 DONALD

0.76

 tweets

0.74

 ترام

0.72

 trump

0.70

 tweet

0.70

Activations Density 0.354%

references to specific individuals and events in political contexts

No Comments

No Known Activations