INDEX

Explanations

spatial relationships and locations of objects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

rawDesc

-0.61

kaper

-0.56

CWE

-0.54

isbury

-0.53

CFA

-0.51

ven

-0.50

таратура

-0.50

anagh

-0.49

usermodel

-0.49

бяза

-0.49

POSITIVE LOGITS

neath

0.86

 derrière

0.85

 Beneath

0.79

 BEHIND

0.79

Beneath

0.78

 beneath

0.77

 bakom

0.75

 Behind

0.74

 debajo

0.72

behind

0.72

Activations Density 0.321%

spatial relationships and locations of objects

No Comments

No Known Activations