INDEX

Explanations

references to economic or operational frameworks

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

EAT

-0.80

Wro

-0.72

mort

-0.72

Luf

-0.71

 Overton

-0.68

 Horton

-0.67

 poffible

-0.67

 Elast

-0.67

 Constan

-0.66

eat

-0.66

POSITIVE LOGITS

 scheme

2.36

scheme

2.33

 SCHEME

2.29

 schemes

2.29

Scheme

2.28

 Scheme

2.26

 Schemes

2.19

schemes

2.13

SCHEME

2.03

Schemes

2.03

Activations Density 0.092%

references to economic or operational frameworks

No Comments

No Known Activations

references to economic or operational frameworks

No Comments

No Known Activations