INDEX

Explanations

references to operating systems, particularly Windows and Linux

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ArgumentParser

-0.86

oredCriteria

-0.75

ślę

-0.74

CodedInputStream

-0.72

envoy

-0.71

 Cuff

-0.70

ximity

-0.67

 Navbar

-0.64

 ConstraintSet

-0.64

 Khal

-0.64

POSITIVE LOGITS

 Windows

1.67

Windows

1.57

 WINDOWS

1.22

windows

1.19

PCs

1.13

PC

1.12

pc

1.04

WINDOWS

1.00

 windows

0.99

pc

0.96

Activations Density 0.046%

references to operating systems, particularly Windows and Linux

No Comments

No Known Activations