INDEX

Explanations

technical terminology and keywords related to system efficiency and performance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 تواند

-0.51

 prochain

-0.50

 확인

-0.49

 somma

-0.48

 prochaines

-0.48

 ytterligare

-0.47

 '').

-0.47

 waaronder

-0.47

lalu

-0.47

onu

-0.47

POSITIVE LOGITS

unlike

1.39

 unlike

1.37

Unlike

1.29

 Unlike

1.28

不像

1.06

compared

0.96

 compared

0.95

 Compared

0.95

Compared

0.93

IndentedString

0.93

Activations Density 0.347%

technical terminology and keywords related to system efficiency and performance

No Comments

No Known Activations