INDEX

Explanations

references to motorcycles and related features in the context of product descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

toplankton

-0.62

 Grinch

-0.49

tagHelperRunner

-0.48

 prisonniers

-0.47

 phytoplankton

-0.46

 تانيه

-0.46

 zwem

-0.45

テニス

-0.44

asantry

-0.44

 spesa

-0.44

POSITIVE LOGITS

 motorcycle

1.13

 Motorcycle

1.01

 motorcycles

0.97

Motorcycle

0.92

 motorbike

0.91

 rider

0.90

 riders

0.90

motorcycle

0.89

 ridden

0.84

 motocic

0.82

Activations Density 0.079%

references to motorcycles and related features in the context of product descriptions

No Comments

No Known Activations