INDEX

Explanations

references to specific locations or designated areas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

íncia

-0.81

 Maier

-0.81

Hauptartikel

-0.78

DoubleQuotes

-0.77

egis

-0.77

 مشين

-0.76

Hydra

-0.75

(!__

-0.73

InputModule

-0.73

 متعلقه

-0.73

POSITIVE LOGITS

 spot

1.98

 Spot

1.89

 SPOT

1.87

spot

1.71

 Spots

1.70

Spot

1.68

 spots

1.65

SPOT

1.63

spots

1.54

Spots

1.31

Activations Density 0.064%

references to specific locations or designated areas

No Comments

No Known Activations