INDEX

Explanations

names of individuals, particularly in a list or directory format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

setVerticalGroup

-0.80

Autoritní

-0.74

الحياه

-0.70

 Савезне

-0.67

Manbalar

-0.65

 مرئيه

-0.63

Kjelder

-0.59

 autorytatywna

-0.59

 Shil

-0.58

 bursa

-0.58

POSITIVE LOGITS

InvalidProtocol

0.57

abetes

0.55

withIdentifier

0.52

 successivo

0.52

MessageTagHelper

0.52

писок

0.51

</strong>

0.50

則是

0.49

creativecommons

0.48

+#+

0.48

Activations Density 0.711%

names of individuals, particularly in a list or directory format

No Comments

No Known Activations