INDEX

Explanations

references to encoding formats or specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

RenderAtEndOf

-0.66

arangay

-0.45

تقاوى

-0.45

persky

-0.40

toMatch

-0.40

 utafitiHapana

-0.39

toBe

-0.39

tagHelperRunner

-0.38

ReusableCell

-0.38

ius

-0.38

POSITIVE LOGITS

StandardCharsets

0.50

IUrlHelper

0.50

 gynhyrchwyd

0.48

ViewFeatures

0.47

 initComponents

0.47

RefNanny

0.47

ISupport

0.44

WebServlet

0.44

ChildScrollView

0.44

 okuyayım

0.43

Activations Density 0.001%

references to encoding formats or specifications

No Comments

No Known Activations