INDEX

Explanations

expressions of surprise or incredulity regarding events or situations

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

niająca

-0.52

 informée

-0.49

ReusableCell

-0.48

AddTagHelper

-0.46

complexType

-0.46

enterOuterAlt

-0.46

sizeCache

-0.46

AutoScaleMode

-0.45

figsize

-0.45

ство

-0.43

POSITIVE LOGITS

 pouvoit

0.53

 auroit

0.47

 Serikat

0.46

 tłuma

0.45

nė

0.43

 geschiedenis

0.43

 abstrato

0.43

 étoit

0.42

 joindre

0.42

 goederen

0.41

Activations Density 1.131%

expressions of surprise or incredulity regarding events or situations

No Comments

No Known Activations