INDEX

Explanations

metadata and document structure elements indicated by specific formatting or punctuation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/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.21.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

 Roskov

-0.67

المناصب

-0.56

 متعلقه

-0.54

 betweenstory

-0.51

 الاطلاع

-0.50

WebVitals

-0.50

AddTagHelper

-0.49

ソッド

-0.46

DeleteBehavior

-0.46

 كورة

-0.46

POSITIVE LOGITS

 ATTENTION

0.58

 Attention

0.55

 conformational

0.53

Fis

0.53

param

0.52

Aves

0.52

ENDIAN

0.51

 pendulum

0.51

 Quark

0.50

 Networks

0.50

Activations Density 0.310%

metadata and document structure elements indicated by specific formatting or punctuation

No Comments

No Known Activations