INDEX

Explanations

references to commands or actions related to software or settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

Ch

-0.93

Ne

-0.92

Ro

-0.90

Du

-0.88

Se

-0.87

Am

-0.86

Su

-0.86

Le

-0.85

Har

-0.85

POSITIVE LOGITS

 disambiguazione

0.81

Autoritní

0.81

 supérieurs

0.78

 Paving

0.77

 découver

0.77

 Wreath

0.77

 cérami

0.77

 Fittings

0.77

 Restra

0.76

 réfrig

0.76

Activations Density 0.057%

references to commands or actions related to software or settings

No Comments

No Known Activations