INDEX

Explanations

non-English words or phrases

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

acamata

-0.74

insegna

-0.71

valently

-0.70

 scheda

-0.67

dür

-0.66

 TAMBÉM

-0.66

لكتر

-0.65

ثیر

-0.64

STRACT

-0.63

idoscope

-0.63

POSITIVE LOGITS

 estekak

0.94

fjspx

0.87

iration

0.86

cination

0.82

ündung

0.81

 متعلقه

0.79

aarrggbb

0.75

 captura

0.75

vation

0.74

uation

0.74

Activations Density 0.008%

non-English words or phrases

No Comments

No Known Activations