INDEX

Explanations

positive descriptors of quality and performance in products or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

المكان

-0.56

yntaxException

-0.52

URLException

-0.50

PasswordEncoder

-0.49

 通販

-0.46

 carriage

-0.45

RefNanny

-0.44

Diwedd

-0.43

inheritDoc

-0.42

SpringRunner

-0.42

POSITIVE LOGITS

zeß

0.40

ycznego

0.36

gląd

0.36

 pelúcia

0.36

produtos

0.35

 própria

0.35

 perfeita

0.34

 datter

0.34

 terbukti

0.34

évaluateur

0.34

Activations Density 0.011%

positive descriptors of quality and performance in products or experiences

No Comments

No Known Activations