INDEX

Explanations

place names and references to specific locations

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

 umane

-0.81

 domestiques

-0.75

 umana

-0.74

 umano

-0.73

 murale

-0.70

 Theſe

-0.69

 russes

-0.68

 lourdes

-0.67

 veneta

-0.67

 rodríguez

-0.67

POSITIVE LOGITS

de

1.46

des

1.05

del

1.02

1.01

du

0.89

di

0.85

 della

0.81

 dels

0.80

 delle

0.77

dei

0.76

Activations Density 0.224%

place names and references to specific locations

No Comments

No Known Activations