INDEX

Explanations

varied categories or types of items or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

fromCharCode

-0.54

BagConstraints

-0.53

 numberWith

-0.52

}")]

-0.50

 cref

-0.50

 definitiv

-0.49

NullException

-0.48

__()

-0.48

LayoutStyle

-0.48

 protoimpl

-0.48

POSITIVE LOGITS

 various

1.01

bagai

1.01

さまざまな

1.00

various

0.98

 įva

0.97

 Various

0.96

Various

0.95

 allerlei

0.93

いろいろな

0.93

 разнообраз

0.93

Activations Density 0.393%

varied categories or types of items or concepts

No Comments

No Known Activations