INDEX

Explanations

phrases indicating contradictions or clarifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

openg

-0.40

 legale

-0.40

FIS

-0.38

OCCURRED

-0.38

ต่อ

-0.38

nościo

-0.38

 ainda

-0.37

AsUp

-0.37

usul

-0.36

nabla

-0.36

POSITIVE LOGITS

oredCriteria

0.81

 oprot

0.75

Попис

0.71

 estekak

0.71

Kanpo

0.69

 propOrder

0.65

ukunft

0.64

 ProtoMessage

0.63

 NSCoder

0.63

0.62

Activations Density 0.337%

phrases indicating contradictions or clarifications

No Comments

No Known Activations