INDEX

Explanations

phrases that indicate recommendations or advice about decision-making

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

expandindo

-0.63

 المعيارى

-0.54

ритори

-0.51

 Complaints

-0.51

onAttach

-0.50

Obrázky

-0.49

tagHelperRunner

-0.49

 complaints

-0.48

Recursion

-0.48

complaint

-0.47

POSITIVE LOGITS

 advisable

0.99

 unwise

0.83

 préférable

0.81

 preferable

0.81

 sebaiknya

0.78

ควร

0.77

Best

0.76

lepiej

0.76

 best

0.76

 advis

0.74

Activations Density 0.350%

phrases that indicate recommendations or advice about decision-making

No Comments

No Known Activations