INDEX

Explanations

specific terms related to scientific publications and their components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 fubject

-0.53

 Paglinawan

-0.52

 GENERATED

-0.51

 cinematogra

-0.50

 figliu

-0.49

 alimentaire

-0.48

Elen

-0.48

 محفوظة

-0.48

 gere

-0.48

 neceffary

-0.48

POSITIVE LOGITS

原始内容存档于

1.06

 Signalez

0.94

Bronnen

0.91

 Roskov

0.88

ⓧ

0.81

 sẻ

0.81

Odkazy

0.78

 SwiftUI

0.78

 <=",

0.74

 مشين

0.72

Activations Density 0.479%

specific terms related to scientific publications and their components

No Comments

No Known Activations