INDEX

Explanations

keywords and symbols related to programming or coding in technical documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 myſelf

-1.37

Efq

-1.32

 himſelf

-1.28

 Jefus

-1.28

 Monfieur

-1.23

 themſelves

-1.21

 itſelf

-1.16

Eſ

-1.15

 Chrift

-1.11

 Houſe

-1.09

POSITIVE LOGITS

0.86

0.81

0.79

0.76

0.75

ha

0.75

al

0.74

con

0.72

un

0.71

Activations Density 0.849%

keywords and symbols related to programming or coding in technical documentation

No Comments

No Known Activations