INDEX

Explanations

phrases and elements related to offers, requests or exchanges

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

Efq

-0.73

 Monfieur

-0.66

BeginInit

-0.64

 becauſe

-0.64

 itſelf

-0.63

 tfsi

-0.61

 Shakspeare

-0.61

存于互联网档案馆

-0.60

ChildScrollView

-0.60

 myſelf

-0.60

POSITIVE LOGITS

Portale

0.58

følgelig

0.54

tableFuture

0.52

che

0.51

 насељу

0.50

med

0.50

tr

0.49

ungsbedingungen

0.49

pooled

0.48

izumi

0.48

Activations Density 0.168%

phrases and elements related to offers, requests or exchanges

No Comments

No Known Activations