INDEX

Explanations

references to geographic locations, especially those labeled as "Central."

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

HMM

-0.74

 ModelExpression

-0.74

 Phry

-0.71

 Sikkim

-0.70

 Yugos

-0.69

 Algerian

-0.67

 Nantucket

-0.66

 Palestinians

-0.66

 Hawai

-0.66

kháu

-0.66

POSITIVE LOGITS

 Central

3.62

 central

3.59

Central

3.51

central

3.36

 CENTRAL

3.23

CENTRAL

3.10

 centrale

2.46

 zentrale

2.36

 sentral

2.33

 centrales

2.23

Activations Density 0.049%

references to geographic locations, especially those labeled as "Central."

No Comments

No Known Activations