INDEX

Explanations

non-zero numerical values and references to funding and acknowledgements in research documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

spec

-0.56

beth

-0.54

lland

-0.49

стей

-0.46

lon

-0.46

both

-0.46

ことも

-0.46

hof

-0.45

Encyklopedia

-0.45

 spec

-0.45

POSITIVE LOGITS

findpost

1.06

WithIOException

0.74

mybatisplus

0.73

UnitTesting

0.68

ьаж

0.64

 vPvB

0.63

]();

0.63

RegressionTest

0.63

 ویکی‌پدی

0.57

 Administrativna

0.56

Activations Density 0.166%

non-zero numerical values and references to funding and acknowledgements in research documents

No Comments

No Known Activations