INDEX

Explanations

terms and concepts related to computational science methods and structures

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

databind

-0.84

Vog

-0.83

otechnology

-0.76

usermodel

-0.74

 Schult

-0.70

 Strom

-0.70

 Bren

-0.69

 cong

-0.69

 Rosal

-0.69

protoimpl

-0.68

POSITIVE LOGITS

 quæ

1.03

 âgées

0.92

 vectorielles

0.90

 Raim

0.87

 omnia

0.86

 drôle

0.84

 Kira

0.82

 Raoul

0.82

">:

0.81

 Jérusalem

0.79

Activations Density 0.520%

terms and concepts related to computational science methods and structures

No Comments

No Known Activations