INDEX

Explanations

locations and spatial relationships between objects or individuals

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

rupal

-0.74

 Erfurt

-0.61

pezif

-0.60

hartt

-0.59

 Makan

-0.58

 Chartres

-0.57

modelBuilder

-0.57

harusnya

-0.55

 daqui

-0.55

 Louie

-0.54

POSITIVE LOGITS

 beside

1.44

 Beside

1.21

 accanto

1.16

 alongside

1.07

 کنار

1.00

 obok

0.89

 рядом

0.86

 naast

0.86

 Alongside

0.84

 neben

0.81

Activations Density 0.074%

locations and spatial relationships between objects or individuals

No Comments

No Known Activations