INDEX

Explanations

terms and structures related to scientific research and data analysis

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ⓧ

-0.79

GEBURTSDATUM

-0.71

OGND

-0.69

 CYTHON

-0.67

 demurrer

-0.66

 ویکی‌پدیا

-0.66

protoimpl

-0.66

AccessorTable

-0.64

$_(

-0.64

 oprot

-0.63

POSITIVE LOGITS

 financières

0.47

 kanssa

0.43

timewa

0.41

 enää

0.40

WAM

0.40

 statt

0.40

 dàng

0.40

uszcz

0.39

0.38

 szint

0.38

Activations Density 0.721%

terms and structures related to scientific research and data analysis

No Comments

No Known Activations