INDEX

Explanations

mentions of proximity or related locations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 pesos

-0.59

 Indias

-0.58

retan

-0.57

 Egon

-0.57

ArrowToggle

-0.56

 ulang

-0.56

sprozess

-0.55

phosa

-0.55

 Shao

-0.54

sproz

-0.54

POSITIVE LOGITS

 neighbors

1.27

Nearby

1.24

 neighbor

1.22

 neighbours

1.20

 neigh

1.18

 Neighbor

1.16

 Nearby

1.13

 neighbour

1.12

 neighboring

1.11

nearby

1.11

Activations Density 0.134%

mentions of proximity or related locations

No Comments

No Known Activations