INDEX

Explanations

technical terms and concepts related to parsing and data processing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

mi

-0.45

а

-0.44

ici

-0.43

mert

-0.43

tu

-0.42

 θέ

-0.41

 spad

-0.41

iz

-0.40

POSITIVE LOGITS

AndEndTag

1.20

esModule

1.13

 Administrativna

0.97

expandindo

0.95

tvguidetime

0.94

+#+#

0.93

Aiheesta

0.93

 تضيفلها

0.90

 intptr

0.87

 chi̍t

0.87

Activations Density 1.039%

technical terms and concepts related to parsing and data processing

No Comments

No Known Activations