INDEX

Explanations

phrases and concepts related to perception and understanding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

AsUp

-0.75

 Kidman

-0.73

weds

-0.72

rawler

-0.72

upaten

-0.70

Optim

-0.70

könyv

-0.70

 referrerpolicy

-0.69

 smtplib

-0.69

 sério

-0.68

POSITIVE LOGITS

 SENSE

1.70

 Sense

1.61

 sense

1.44

Sense

1.43

 senses

1.32

sense

1.32

 Senses

1.15

 sensed

1.13

 SENS

1.02

 sens

1.02

Activations Density 0.055%

phrases and concepts related to perception and understanding

No Comments

No Known Activations