INDEX

Explanations

phrases indicating proximity or spatial relations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

aurus

-0.84

harusnya

-0.81

ftagPool

-0.81

 Esposito

-0.80

 dalamnya

-0.76

TAWA

-0.73

 continúas

-0.72

 iParam

-0.70

 Boles

-0.70

ellschaft

-0.69

POSITIVE LOGITS

 NEAR

1.44

NEAR

1.41

near

1.38

 Near

1.35

 near

1.33

Near

1.20

 nearer

0.93

cerca

0.89

ness

0.89

 gần

0.81

Activations Density 0.067%

phrases indicating proximity or spatial relations

No Comments

No Known Activations