INDEX

Explanations

inquiries related to processes or operations, especially those beginning with "how" or "what."

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

Efq

-0.82

 Shaksp

-0.70

 houſe

-0.68

 virginity

-0.66

 Cæsar

-0.66

 Theſe

-0.66

 ujednoznacz

-0.65

 للاسماء

-0.65

сылкі

-0.65

 Houſe

-0.64

POSITIVE LOGITS

SpringRunner

0.65

 onOptions

0.64

AndroidJUnit

0.61

 agrí

0.57

ArgumentParser

0.57

TabStop

0.55

CascadeType

0.55

WithMany

0.54

how

0.53

addGap

0.53

Activations Density 0.145%

inquiries related to processes or operations, especially those beginning with "how" or "what."

No Comments

No Known Activations