INDEX

Explanations

references to additional information, resources, or guidance on various policies and topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 <<<<<<<<<<<<<<

-0.63

 "..\..\..\

-0.55

initComponents

-0.55

 Савезне

-0.54

sizeCache

-0.51

UnitTesting

-0.50

ViewImports

-0.50

Vorte

-0.47

 "..\..\

-0.47

UserScript

-0.47

POSITIVE LOGITS

 details

0.68

 Details

0.60

詳しくは

0.55

详情

0.54

details

0.54

详细信息

0.52

 info

0.50

робнее

0.50

 addSubview

0.49

Details

0.48

Activations Density 0.287%

references to additional information, resources, or guidance on various policies and topics

No Comments

No Known Activations