INDEX

Explanations

terms related to registration or categorization processes

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

MENAFN

-0.52

 Waray

-0.50

 Wicidata

-0.45

kuuta

-0.45

ISupport

-0.44

jooq

-0.43

 trovato

-0.40

 κό

-0.40

مقاله

-0.39

 tappa

-0.39

POSITIVE LOGITS

ering

1.00

ered

1.00

erex

0.95

ers

0.93

ERS

0.91

ERING

0.90

ters

0.90

ership

0.85

tered

0.84

erval

0.84

Activations Density 0.395%

terms related to registration or categorization processes

No Comments

No Known Activations