INDEX

Explanations

solutions to programming or coding issues

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

WithIOException

-0.79

rrggbb

-0.75

elemField

-0.74

IntoConstraints

-0.72

ſelf

-0.71

 linkovi

-0.70

Vidite

-0.69

Hochspringen

-0.68

Hentet

-0.68

velocityY

-0.65

POSITIVE LOGITS

 alternative

0.60

 alternatively

0.57

 alternate

0.57

 либо

0.56

 Alternatively

0.55

 ALTERNATIVE

0.55

Alternatively

0.52

un

0.51

 another

0.51

 temporarily

0.51

Activations Density 0.551%

solutions to programming or coding issues

No Comments

No Known Activations