INDEX

Explanations

mentions of proximity or nearness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

harusnya

-0.76

ftagPool

-0.74

-0.73

 iParam

-0.73

 uParam

-0.72

QMetaType

-0.71

 dalamnya

-0.65

 pstmt

-0.64

aurus

-0.63

 Esposito

-0.63

POSITIVE LOGITS

near

2.16

 near

2.12

 Near

2.04

 NEAR

1.99

Near

1.94

NEAR

1.83

 nearer

1.21

 Cerca

1.19

 cerca

1.14

 nearby

1.11

Activations Density 0.049%

mentions of proximity or nearness

No Comments

No Known Activations