INDEX

Explanations

terms and phrases indicating conditions, limitations, or warranty issues related to software or services

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

bes

-0.59

 cejas

-0.52

</i>

-0.51

 move

-0.49

 deliberately

-0.49

hskip

-0.49

the

-0.46

mas

-0.46

>{"

-0.45

glyphicon

-0.45

POSITIVE LOGITS

tagHelperRunner

0.98

 дописавши

0.87

Sucesor

0.84

 snippetHide

0.77

 الاطلاع

0.74

المناصب

0.74

Tembelea

0.74

 cherchés

0.74

 <<<<<<<<<<<<<<

0.73

 виправивши

0.73

Activations Density 0.002%

terms and phrases indicating conditions, limitations, or warranty issues related to software or services

No Comments

No Known Activations