INDEX

Explanations

mathematical notations and symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

efec

-0.49

labelledby

-0.45

GrantedAuthority

-0.44

AutoScale

-0.43

AsyncResult

-0.43

멀

-0.42

 ModelRenderer

-0.42

лично

-0.42

nex

-0.41

NegativeButton

-0.40

POSITIVE LOGITS

WEBPACK

5.87

interopRequire

1.45

 متعلقه

1.20

 CreateTagHelper

1.15

 تضيفلها

1.04

BeginContext

0.95

 فريبيس

0.92

__(/*!

0.90

 estekak

0.90

adə

0.90

Activations Density 0.015%

mathematical notations and symbols

No Comments

No Known Activations