INDEX

Explanations

terms related to rewriting and updating content or code

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

Odkazy

-0.69

mobileqq

-0.66

brainly

-0.65

__((

-0.64

mybatisplus

-0.63

 ComVisible

-0.63

 HttpNotFound

-0.63

wpi

-0.62

contentLoaded

-0.62

minecraftforge

-0.59

POSITIVE LOGITS

Rew

1.10

 Rebuild

1.06

 reissue

1.05

 recast

1.05

 reposition

1.01

 rebuilding

1.00

 rebuild

0.97

 reformat

0.97

 reinstatement

0.96

 readjust

0.96

Activations Density 0.283%

terms related to rewriting and updating content or code

No Comments

No Known Activations