INDEX

Explanations

references to programs or initiatives, particularly in the context of healthcare or educational contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 cheeks

-0.77

etches

-0.76

ECTS

-0.76

itattu

-0.75

 larmes

-0.74

createCell

-0.72

 thous

-0.71

 visuales

-0.71

clusal

-0.70

EDEFAULT

-0.70

POSITIVE LOGITS

 programs

1.46

 programmes

1.30

Programs

1.27

 program

1.25

 Programs

1.24

programs

1.22

PROGRAM

1.21

 Program

1.12

 programme

1.12

 progra

1.10

Activations Density 0.050%

references to programs or initiatives, particularly in the context of healthcare or educational contexts

No Comments

No Known Activations