INDEX

Explanations

references to specific geographic locations and addresses

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

 intptr

-0.63

 Jacinto

-0.53

Emi

-0.51

 Gump

-0.51

keo

-0.51

 Kolo

-0.50

例句

-0.50

PerformLayout

-0.49

 Timur

-0.49

POSITIVE LOGITS

 Rockland

0.74

 Westchester

0.70

Geplaatst

0.57

 Bergen

0.55

Demografía

0.53

Dut

0.52

 Bronx

0.52

 Hudson

0.52

Cro

0.50

 Orange

0.50

Activations Density 0.099%

references to specific geographic locations and addresses

No Comments

No Known Activations