INDEX

Explanations

specific numerical values or counts related to experimental data

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

 Cowper

-0.82

orothy

-0.79

 Shire

-0.75

ilius

-0.72

Mey

-0.71

 StatefulWidget

-0.70

multer

-0.70

 Ching

-0.70

 Robin

-0.70

 Blok

-0.69

POSITIVE LOGITS

UNRELATED

0.71

 foncé

0.70

Jop

0.70

 Tana

0.69

atorze

0.69

 Jamb

0.68

 frequenza

0.67

 setOpen

0.66

almaz

0.66

 Jambi

0.65

Activations Density 0.615%

specific numerical values or counts related to experimental data

No Comments

No Known Activations