INDEX

Explanations

references to lasers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

:+:

-0.63

 indeed

-0.59

ifrance

-0.56

 errori

-0.54

 Mahat

-0.54

 مشين

-0.54

 ISNI

-0.53

ducteur

-0.51

ற்

-0.49

mistry

-0.49

POSITIVE LOGITS

 slightest

0.91

 lasers

0.80

 laser

0.79

 thousand

0.77

 Laser

0.76

thousand

0.75

nalités

0.72

Laser

0.72

 Jefus

0.71

 Forumite

0.70

Activations Density 0.062%

references to lasers

No Comments

No Known Activations