INDEX

Explanations

references to "mono" and variations of brightness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 becauſe

-1.01

 ſeveral

-1.00

 Theſe

-0.99

 itſelf

-0.96

 againſt

-0.94

 myſelf

-0.94

 purpoſe

-0.93

 Majefty

-0.88

 ſame

-0.88

 laſt

-0.88

POSITIVE LOGITS

PerformLayout

0.74

mon

0.72

pat

0.65

 LoggerFactory

0.64

 bright

0.62

My

0.62

0.60

mon

0.57

σταση

0.56

getMonth

0.56

Activations Density 0.115%

references to "mono" and variations of brightness

No Comments

No Known Activations