INDEX

Explanations

references to notes or written records

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

scrollTop

-0.64

 Paix

-0.61

 AssemblyProduct

-0.58

hynch

-0.55

colgroup

-0.54

GraphicsUnit

-0.54

cstdlib

-0.54

stridium

-0.54

 Brito

-0.54

AsUp

-0.53

POSITIVE LOGITS

 notes

3.87

 Notes

3.53

notes

3.35

 note

3.29

Notes

3.19

 NOTES

3.06

note

2.67

 Note

2.65

NOTES

2.56

 notas

2.43

Activations Density 0.080%

references to notes or written records

No Comments

No Known Activations