INDEX

Explanations

concepts related to inclusion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

unteers

-0.71

 AssemblyTitle

-0.68

subpackage

-0.65

signable

-0.64

setupUi

-0.63

DockStyle

-0.62

 AppBundle

-0.60

етка

-0.59

ControllerTest

-0.59

GEBURTSDATUM

-0.58

POSITIVE LOGITS

 resting

0.79

Broker

0.77

 Broker

0.74

Bas

0.72

resting

0.70

AutoresizingMask

0.70

Bas

0.70

ston

0.69

bas

0.68

timestamp

0.67

Activations Density 0.057%

concepts related to inclusion

No Comments

No Known Activations