INDEX

Explanations

phrases indicating spatial relationships or locations relative to objects

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

ſelf

-0.66

hdashline

-0.65

orianCalendar

-0.65

Efq

-0.62

 Cæsar

-0.61

usermodel

-0.61

ſelves

-0.60

felves

-0.60

neſs

-0.56

 houſe

-0.55

POSITIVE LOGITS

 فريبيس

0.77

 behind

0.74

neath

0.70

 beneath

0.70

 Behind

0.66

 derrière

0.66

Behind

0.64

 BEHIND

0.64

 debajo

0.63

 underneath

0.62

Activations Density 0.302%

phrases indicating spatial relationships or locations relative to objects

No Comments

No Known Activations