INDEX

Explanations

references and citations in discussions or arguments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

WillAppear

-0.47

 parti

-0.45

 Parte

-0.45

logging

-0.43

 Rukh

-0.43

Enlaces

-0.42

لينكات

-0.42

 تعدى

-0.42

 partie

-0.41

หาร

-0.41

POSITIVE LOGITS

Попис

0.78

 BorderRadius

0.77

 mergeFrom

0.77

#+#

0.74

 according

0.69

cinogenicity

0.69

 ifølge

0.69

 Dijo

0.69

 AssemblyCompany

0.69

Says

0.69

Activations Density 0.502%

references and citations in discussions or arguments

No Comments

No Known Activations