INDEX

Explanations

evidence of specific regulatory or classification descriptors related to non-parameterized conditions or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 italienne

-0.51

 gjerne

-0.50

 nutricional

-0.50

 læng

-0.50

 hidupnya

-0.50

 נוספת

-0.50

ientôt

-0.49

 garanzia

-0.49

 Litu

-0.49

 podjet

-0.47

POSITIVE LOGITS

Non

1.02

non

1.01

Non

1.00

非

0.99

 CommonModule

0.98

NON

0.97

non

0.92

NON

0.89

expandindo

0.89

 nong

0.87

Activations Density 0.093%

evidence of specific regulatory or classification descriptors related to non-parameterized conditions or statistics

No Comments

No Known Activations