INDEX

Explanations

references to spreadsheets and related documentation

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

dollis

-0.93

TagMode

-0.88

reportWebVitals

-0.88

BagConstraints

-0.87

+#+

-0.83

—

-0.81

Efq

-0.79

inSlope

-0.77

 Prag

-0.77

 تضيفلها

-0.76

POSITIVE LOGITS

 sheet

1.88

 sheets

1.86

 SHEET

1.75

 Sheet

1.71

 Sheets

1.68

sheet

1.68

Sheet

1.67

Sheets

1.65

sheets

1.54

SHEET

1.42

Activations Density 0.069%

references to spreadsheets and related documentation

No Comments

No Known Activations