INDEX

Explanations

numerical data and references related to programming or technical specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

TagMode

-0.55

InputBorder

-0.45

ScopeManager

-0.43

ніципалі

-0.41

bram

-0.40

ResponseWriter

-0.40

 JTextField

-0.40

saraba

-0.40

Bout

-0.40

mert

-0.40

POSITIVE LOGITS

 nahilalakip

0.50

pisode

0.43

ائج

0.39

 Hirst

0.39

ardust

0.39

 NSCoder

0.38

liš

0.35

adpleegd

0.35

íslu

0.34

 testemun

0.34

Activations Density 0.450%

numerical data and references related to programming or technical specifications

No Comments

No Known Activations