INDEX

Explanations

references to significant political events and controversies

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

AxisAlignment

-0.50

 حد

-0.49

XMLSchema

-0.43

 forState

-0.42

 numberWith

-0.42

Gruß

-0.41

 clef

-0.38

 Krzyż

-0.38

 idées

-0.37

 individuale

-0.37

POSITIVE LOGITS

 fires

0.84

 wildfires

0.84

省市镇

0.80

 incendie

0.76

fires

0.76

 ویکی‌پدی

0.76

 Roskov

0.75

NUMX

0.73

 Fires

0.72

NamedQueries

0.71

Activations Density 0.625%

references to significant political events and controversies

No Comments

No Known Activations