INDEX

Explanations

features of a product or invention related to its design and functionality

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

สิน

-0.49

isSuccessful

-0.49

 šķ

-0.49

 zrobi

-0.49

 paura

-0.49

 forhold

-0.48

 parlent

-0.47

cerrar

-0.45

 viņ

-0.45

 disposent

-0.45

POSITIVE LOGITS

 containing

1.13

 comprising

0.99

 belonging

0.99

 consisting

0.98

 involving

0.95

containing

0.95

 totaling

0.91

 representing

0.91

 Containing

0.91

 featuring

0.87

Activations Density 0.720%

features of a product or invention related to its design and functionality

No Comments

No Known Activations

features of a product or invention related to its design and functionality

No Comments

No Known Activations