INDEX

Explanations

phrases indicating relationships or connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

pherals

-0.58

LookAnd

-0.53

 DBNull

-0.51

¿

-0.50

jkl

-0.49

ịch

-0.49

chaffen

-0.48

goblin

-0.46

¿

-0.46

rale

-0.46

POSITIVE LOGITS

addTo

0.86

 addTo

0.78

 tillegg

0.77

 bestehende

0.76

BackStack

0.73

 rejoindre

0.71

 løpet

0.70

 '+':

0.70

asteroide

0.69

 existing

0.69

Activations Density 0.204%

phrases indicating relationships or connections

No Comments

No Known Activations