INDEX

Explanations

references to research methods and study design

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 متعلقه

-0.89

脚注の使い方

-0.84

จึง

-0.60

Facades

-0.60

IVEREF

-0.57

+#+#

-0.56

carpus

-0.56

ERVIEW

-0.55

]=>

-0.55

ándor

-0.55

POSITIVE LOGITS

何より

0.70

CppMethod

0.57

そもそも

0.53

 vulgares

0.51

 also

0.51

 сами

0.49

also

0.49

 विश्वसनीयता

0.48

 defaultstate

0.48

 saites

0.48

Activations Density 0.842%

references to research methods and study design

No Comments

No Known Activations