INDEX

Explanations

non-English characters and symbols

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

GeoNames

-0.67

HasForeignKey

-0.66

TintMode

-0.64

 AssemblyVersion

-0.64

 flé

-0.63

ViewImports

-0.62

 newOwner

-0.62

audiovisuel

-0.61

balleur

-0.61

 Bioaccumulative

-0.61

POSITIVE LOGITS

ⓧ

1.01

 թվական

0.87

حياتها

0.72

nloa

0.65

unsplash

0.63

 елның

0.62

tvguidetime

0.61

copyOf

0.60

НИК

0.60

specifier

0.59

Activations Density 0.141%

non-English characters and symbols

No Comments

No Known Activations