INDEX

Explanations

phrases related to timeframes or durations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 algún

-0.54

 some

-0.53

 somehow

-0.53

 alguna

-0.51

有一种

-0.50

éroport

-0.49

 něk

-0.49

 suatu

-0.49

一部

-0.49

 τὴν

-0.48

POSITIVE LOGITS

 hundred

1.54

 dozen

1.38

 thousand

1.27

 weeks

1.25

hundred

1.19

 months

1.09

dozen

1.03

 hundert

0.99

thousand

0.99

 days

0.98

Activations Density 0.125%

phrases related to timeframes or durations

No Comments

No Known Activations